AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling

Kyunghoon Hur, Eunjung Jeon, Hyun Woo Kim, Gyubok Lee, Seongjun Yang

While deep learning has accelerated drug discovery, its impact on biomanufacturing has been considerably more limited. The reason is data scarcity. Bioreactor experiments are high-cost, take days to weeks, and are rarely shared in public form, leaving each research work with only a handful of experiments. The domain itself, however, is rich in prior knowledge. Biokinetic ordinary differential equation (ODE) models have described microbial growth for decades, yet how to inject this knowledge into a neural network has not been studied systematically. We present the first systematic study of how to inject this ODE knowledge into a neural network, comparing a data-level prior that pre-trains a generic decoder on simulated ODE curves against an architecture-level prior that embeds the ODE inside the decoder. Both consistently outperform no-prior baselines across 11 datasets and 7 microbial species. Our central finding is that the two are substitutable. A generic decoder pre-trained on simulation matches a fully bio-structured decoder trained on real data. Simulation pre-training therefore offers a simple, data-efficient recipe for deep learning under bioprocess data scarcity.

arXiv

Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches

Yitao Jiang, Yaoqing Yang, Luyang Zhao, Muhao Chen, Devin Balkcom

Long-context Transformer inference increasingly relies on KV-cache compression or quantization. Prior rotation and transform-coding results suggest that the channel basis of each key/value vector affects how faithfully a fixed backend preserves model behavior. We introduce Codec-Gauge, a post-training cache-coordinate layer that learns small orthogonal channel transforms around existing compression and quantization backends. Its frequency-distribution objective combines a token-channel DCT spectral-centroid loss with a smooth rate proxy to concentrate KV energy in low-frequency codec-facing layouts. We evaluate actual compression and decompression using measured bytes and rolling compressed-history scoring. Across six models at $3$, $4$, and $6$ bits/value, learned gauges reduce zfp KL divergence by $44.0\%$ on average relative to raw coordinates and outperform random, Hadamard, DCT, and PCA/KLT controls. The same gauges improve quality preservation for block-uniform and KIVI-style quantization. Experiments on a 27B model and long-context task prompts reproduce the quality trend, while serial storage and timing measurements validate the implemented compressed-cache paths. These results establish cache-coordinate geometry as a practical post-training variable for improving compression fidelity without changing model weights, attention semantics, or backend coding rules.

arXiv

ReliableTableQA:How Much Supervision Does Reliability Annotation Need?

Huei-Chung Hu, Hsin-Tai Wu, Koyo Kobayashi

We introduce ReliableTableQA, a framework for training an LLM to annotate the statistical reliability of tabular QA results, not whether the query is answerable, but whether the computed answer is statistically meaningful. In real enterprise analytics, a syntactically correct SQL query can return a value that is based on too small a sample, has an excessively wide confidence interval, or is too confounded to support action. Existing systems answer confidently in all such cases, a failure we quantify as the Unreliable Confident Answer Rate (UCAR). We contribute (1) a ten-category reliability taxonomy (R1-R10) covering hazards such as small-sample aggregates, multiple-comparison inflation, and distribution-tail mismatch; (2) a program-first data pipeline that generates 50,000 reliability-labeled training examples from a context-free grammar over public retail schemas, with schema-stratified SFT/GRPO splits; and (3) a controlled study of how much supervision calibrated reliability annotation actually requires. We find that a small, schema-stratified SFT set is remarkably sufficient: 200 examples raise reliability-flag F1 from 0.61 to 0.98 and parse rate from 0.52 to 1.00, drive UCAR to zero, and yield a model that generalizes to an unseen retail domain (Rel-F1 0.997 on held-out H&M). Against this strong SFT baseline, GRPO, commonly assumed to be essential, helps only when SFT is under-trained (+0.06-0.16 exact-flag-set match at 100 examples, in- and out-of-distribution) and provides no measurable benefit once SFT is adequate, a null result we confirm across a hard compound-flag slice, a strict exact-match metric, and out-of-distribution evaluation. Our findings reframe reliability annotation as a data-efficiency problem and delineate precisely when reinforcement fine-tuning does and does not pay off.

arXiv

Grounding Investor Views: Neural Predicates in the Black-Litterman Model

Marcos Florencio

Portfolio construction under the Black-Litterman model requires investors to specify views on asset returns alongside explicit uncertainty estimates -- a process that remains largely subjective and difficult to scale. We propose a formal approach in which neural predicates serve as a structured, probabilistic mechanism for view generation. In our formulation, structured financial analysis data is processed through a compositional hierarchy of neural predicates whose outputs -- probability distributions over market stances -- are mapped to the pick matrix $\mathbf{P}$, the view return vector $\mathbf{q}$, and the view uncertainty matrix $\boldsymbolΩ$ of the Black-Litterman model. View confidence is derived from predicate output distributions, providing a data-driven alternative to subjective uncertainty elicitation. The resulting approach is interpretable, in the sense that any portfolio weight can be traced back through the predicate's logical chain to the underlying data, and fully differentiable, enabling end-to-end learning.

arXiv

Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development

Nadine Chang, Maying Shen, Jialiang Wang, Rafid Mahmood, Jose M. Alvarez

Many modern AI systems are designed to operate under diverse, open-ended, use-cases. To help generalize deployed systems, many deployed-system maintenance pipelines use a reactive AI flywheel that observes emerging feedback from user behavior (errors) and patches the model accordingly. However, when used as the primary maintenance mechanism, these flywheels often ignore the broader context of these errors within the system's objectives, failing to preempt potential future edge cases, which leads to more unnecessary flywheel iterations. Also, it is statistically increasingly difficult to collect remaining errors due to the long-tail nature of open-world use-cases. This position paper argues that a proactive test-driven flywheel is required to address reactive flywheel's limitations and to approach a generalizable system. We advocate for creating a "test space" to technically map feedback data to task objectives, evolving the flywheel from reactive to proactive. We augment our position by mathematically proving a proactive one achieves better long-term scaling with fewer iterations than the reactive flywheel.

arXiv

DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers

Jerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov, Sergey Chuprin, Kirill Redko, Aidar Shumbalov, Anna Kalyuzhnaya

Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score the final answer or a fixed "ground-truth" list of tools, both of which are fragile once the underlying data is live and stateful. We present DynamicMCPBench, a reusable framework rather than a fixed dataset. A practitioner can run it on their own MCP servers to test models on their own tasks, or let it collect servers automatically to measure a model's general ability to solve agentic tasks. Given the servers and any set of models, it generates realistic goals, pursues each one live to record a successful trajectory, distills that trajectory into path-agnostic effect checkpoints, and scores an agent on whether it reproduces those effects, never on the final answer. To show what the framework reveals, we run it at scale: 24 models over 121 servers and 750 tasks spread evenly over 15 task categories (50 each), where each category targets a distinct tool-use challenge of the generated questions. Each task is scored by pass^3: it counts as solved only if all three independent attempts succeed. Even the strongest agents solve only about half of the tasks, 31% of tasks are solved by no model at all, and accuracy collapses as the required tool chain grows longer (from 39% on the shortest chains to 13% on the longest). A human validation study confirms the automatic scoring is reliable (chance-corrected agreement of 0.76). DynamicMCPBench thus turns benchmark construction into something practitioners can rerun on their own servers and models, while exposing a consistent inability of current agents to handle long, multi-step agentic tasks.

arXiv

PromptPack: Scaling LLM Annotation Agents for Online Recommendation

Sebastian Koralewski, Merwan Barlier, Yulia Stolin, Blaž Škrlj

Online recommendation platforms increasingly use Large Language Models (LLMs) to extract structured features from ad creatives. While deploying a single-call LLM annotation agent yields significant Click-Through Rate (CTR) improvements in our live production environment, per-creative prompting is prohibitively expensive to scale. The redundant system instructions sent in every request account for 94% of billed input tokens. To break this cost bottleneck, we introduce PromptPack, a scalable, high-throughput LLM annotation agent. PromptPack achieves this scale via in-context batching, combining a shared system prompt, a strict XML structural envelope, and an output correction layer to ensure deterministic, pipeline-ready feature extraction across multiple creatives simultaneously. We evaluate PromptPack via an offline retrieval benchmark using a downstream logistic-regression ranker. To deeply profile the agent's behavior, we measure AUC and introduce Volume-Weighted Absolute Lift (VWAL), a novel metric capturing the signal quality of the generated features. Compared to our live, unbatched production baseline, PromptPack at batch size 20 cuts our LLM costs by 89% and accelerates throughput by 2.5x while fully preserving AUC.

arXiv

Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis

Taewan Goo, Junsik Kim, Kyulhee Han, GwonYul Jo, Jong-Soo Kim, Tae-Hyung Kim

Agentic LLM systems such as OpenScholar and PaperQA2 read the scientific literature and return cited answers, and both they and their benchmarks already check whether those citations hold, with a fixed attribution model or human graders. Neither audits the reliability of that check itself. We show it is not reliable, and that this matters. On identical agent outputs the measured unsupported-citation rate ranges from about 3% to about 18% depending only on the verifier's strictness, and although verifiers agree on which citations are supported, they disagree on which to flag (negative-specific agreement 0.27 to 0.30), so no single flag set is trustworthy and cross-paper comparison is invalid without a named verifier and protocol. We present a gold-anchored evaluation protocol and a deployable guard that make this behavior measurable and bounded. The protocol validates the verifier, measures re-attribution, and calibrates a guarantee against human gold rather than another model's verdict; the verifier is a swappable instrument chosen on cost (recall 0.94 on the supported class, held out), and re-attribution is a commodity step where a deterministic BM25 matches the best open generator. The guard adds a split-conformal layer placing a distribution-free, finite-sample bound on truly unsupported citations that slip past a chosen flagging rule, a guarantee on catch rate rather than conclusion correctness. The bound holds on held-out gold, and we identify and quantify the condition governing its transfer to deployment, calibration-negative difficulty, with a concrete recalibration recipe, left untested by prior conformal-factuality work. Validated across four open 27-35B models and three agentic pipelines on public benchmarks (SciFact, QASA, PubMedQA), with confidence intervals on every headline number, the protocol and guard ship as an open single-GPU kit.

arXiv

CLOE: Christoffel Loss Autoencoder for Anomaly Detection

Léa Billet, Louise Travé-Massuyès, Elodie Chanthery, Alexandre Gaffet

Semi-supervised anomaly detection plays a key role in diverse fields such as process monitoring, healthcare, and finance. However, lightweight methods often struggle with high-dimensional data and typically require careful tuning of multiple hyperparameters. Among existing approaches, Christoffel Function--based methods are attractive due to their simplicity, requiring at most a single hyperparameter. They also benefit from a well-established theoretical foundation that yields several interesting results for data science. However, their main limitation is poor scalability to high-dimensional settings. In this paper, we introduce CLOE, a new method that combines an autoencoder for dimensionality reduction with a Christoffel Function--based detector applied in the latent space. To better align representation learning with anomaly detection, we design a novel loss function that leverages the Christoffel Function to guide the autoencoder toward representations that better capture the support of the normal data distribution. We further propose a principled procedure to set the detection threshold and an efficient strategy to tune the single remaining hyperparameter. Experiments on multiple high-dimensional tabular anomaly detection benchmarks demonstrate that CLOE achieves superior performance compared to existing methods, while preserving the lightweight and low-tuning advantages of Christoffel Function--based approaches.

arXiv

Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement

Jiawei Zheng, Jiazhen Zhang

Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs. However, existing aggregation methods typically assume that all models are equally trustworthy, overlooking differences in uncertainty quality. This assumption is poorly suited to heterogeneous LLMs, whose reliability and capability vary significantly, making naive aggregation vulnerable to unreliable or adversarial experts. In this work, we formulate multi-LLM aggregation as a problem of uncertainty-aware trust estimation. We adapt structured expert judgment from decision theory, using context-aware calibration questions to estimate expert reliability based on the quality of its probabilistic predictions. Specifically, we employ Cooke-style log weighting, which penalises overconfident incorrect predictions and favours well-calibrated experts. We evaluate our approach on MMLU and MMLU-Pro across homogeneous, heterogeneous, and contaminated expert panels. Results show that while aggregation methods perform similarly in homogeneous settings, Cooke weighting becomes critical under heterogeneity and contamination. It achieves a superior accuracy-reliability balance and remains robust when unreliable experts are introduced. These findings suggest that Multi-LLM aggregation requires not just combining predictions, but calibrating trust under uncertainty.

arXiv

ConfidenceBench: Evaluating Confidence Calibration in Large Language Models

Matthew ffrench-Constant, Daniel Yang, Xinmeng Huang, Sanyam Kapoor

Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy alone is insufficient: models must also know when they are likely to be wrong. We present ConfidenceBench, a calibration benchmark that evaluates verbalized confidence estimates in 15 frontier LLMs using the Brier score, a proper scoring rule that incentivises truthful probability reporting. Confidence is elicited via prompting, requiring no access to model logits and making the framework applicable to both closed-source and open-source systems. The benchmark comprises 200 private multiple-choice questions across four categories: spatial reasoning, high-precision mathematics, word lookup, and unknowable questions. Across three independent runs, Claude Opus 4.6 and Gemini 3.1 Pro Preview achieve the lowest Brier scores, both reported as 0.103. Both substantially outperform the calibrated-random baseline of 0.1875, while Gemini 3.1 Flash-Lite scores 0.367, indicating severe miscalibration. Accuracy and calibration diverge substantially across model families: the most accurate model is not the best-calibrated, and several models perform worse than the calibrated-random Brier baseline despite reasonable accuracy. These results show that verbalized confidence calibration is a distinct and practically important axis of LLM reliability, complementary to standard accuracy-based evaluation.

ICML 2026

Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance

Jingwei Zhang, Haoyu LEI, Zijin Feng, Jiacheng Sun, Farzan Farnia

Although diffusion models have revolutionized continuous domains like image synthesis through high quality generations and controllable guidance mechanisms, bringing this controllability to the discrete, sequential nature of text remains an open challenge. Meanwhile, current sampling strategies and guidance methods adjust token likelihoods without capturing the broader semantic landscape, leading to a suboptimal balance between fidelity and diversity. In this work, we introduce a novel training-free Semantic-Aware Kernel Entropy (SAKE) guidance method. Our method computes the order-2 Rényi entropy over a kernel Gram matrix that captures both cross-token semantic interactions and relative token positions. By linearizing this objective in the embedding space, we derive a tractable guidance signal that dynamically adjusts the sampling distribution—flattening it to encourage exploration during redundancy and sharpening it for fidelity when diverse. Empirical experiments demonstrate that our approach achieves a superior Pareto frontier between fidelity and diversity, and improves multi-sample performance on reasoning-intensive tasks, such as code and mathematics generation, compared to temperature scaling and discrete guidance baselines.

arXiv

Text-based Tactile Graphics Generation for the Visually Impaired

Ruihan Gao, Joonghyuk Shin, Ava Pun, Jaesik Park, Wenzhen Yuan, Jun-Yan Zhu

Tactile graphics are a primary medium for blind and low-vision (BLV) individuals to access non-textual information. However, they are difficult to scale or personalize. While recent generative models have revolutionized visual content creation, they are optimized for screen-based visual realism and fail to satisfy the haptic perceptual and physical fabrication constraints required for touch. We present the first integrated generative system that produces fabrication-ready 2.5D tactile graphics directly from natural language prompts, jointly generating global base geometry, fine-grained tactile surface textures, and standard-compliant braille within a unified 3D-printable representation. Our approach introduces fabrication-aware techniques, including template-guided relief generation, a fast diffusion-based text-to-texture module for high-resolution tileable normal maps, and strict base flattening to ensure tactile readability and printability, while supporting both automatic generation and interactive texture control. Extensive evaluations, together with in-person user studies with BLV participants and blindfolded sighted participants using physically 3D-printed outputs, show that participants consistently prefer our results over baselines. By extending generative graphics beyond screens to touchable reliefs, our work broadens access to generative AI for the BLV community and beyond.

arXiv

AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders

Georgios Anyfantis, Pere Barlet-Ros

Network Intrusion Detection Systems (NIDS) are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and characterisation, these methods require accurately labelled datasets, which are very costly to obtain. Moreover, existing public datasets have limited and/or outdated attacks, and many of them suffer from mislabelled data. To reduce the reliance on labelled data, we propose AutoGraphAD, a novel unsupervised anomaly detection approach based on a Heterogeneous Variational Graph Autoencoder. AutoGraphAD operates on heterogeneous graphs, made from connection and IP nodes that represent network activity. The model is trained using unsupervised and contrastive learning, without relying on any labelled data. The model's losses are then weighted and combined in an anomaly score used for anomaly detection. Overall, AutoGraphAD yields the same, and in some cases better, results than Anomal-E, but without requiring costly downstream anomaly detectors. As a result, AutoGraphAD achieves around 1.18 orders of magnitude faster training and 1.03 orders of magnitude faster inference, which represents a significant advantage for operational deployment.

arXiv

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

James Elcock, William F. Shen, Xinchi Qiu, Nicholas D. Lane

Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a model's pre-existing alignment, especially its safety behavior, its broader effects across alignment domains remain poorly understood. We address this gap through a systematic evaluation of representative task-adaptation methods, including supervised fine-tuning (SFT), KL-regularized SFT, and reinforcement learning with verifiable rewards (RLVR) across 15 alignment aspects spanning six key domains: safety, factuality, stance stability, social harm, controllability, and instructability. Our results reveal that post-training does not reshape alignment uniformly. RLVR improves task performance while inducing comparatively small, but non-zero, metric-specific shifts, while SFT leads to substantially larger alignment drift across domains. KL regularization mitigates this effect: stronger reference-model anchoring reduces alignment drift from the baseline, although KL-SFT still falls short of RLVR in preserving alignment. Representation-level analysis further supports this pattern, with shifts in alignment-relevant representations tracking behavioral drift. Together, these results show that task adaptation is not merely a capability-improving step, but an alignment intervention in its own right, motivating multi-dimensional alignment evaluation as a standard component of post-training pipelines.

arXiv

A Graph Neural Network approach to zero-shot Digital Twins

Alicia Tierz, Icíar Alfaro, David González, Elías Cueto

Traditional Predictive Digital Twins often remain geometrically rigid, requiring extensive retraining or fine-tuning whenever the underlying physical domain or boundary conditions change. To overcome this limitation, we present a novel framework for \textit{Zero-Shot Digital Twins} that seamlessly couples real-time visual perception with a geometry-agnostic, physics-informed reasoning engine. At the core of our architecture is the Thermodynamics-Informed Graph Neural Network architecture, a Geometric Deep Learning solver grounded in a metriplectic thermodynamic formalism that enforces energy conservation and non-negative entropy production locally through graph message passing. The framework integrates an auxiliary Graph Neural Network to infer unobservable fields (such as stress tensors or velocity and energy distributions) directly from sparse initial visual boundaries, mitigating numerical start-up transients. To bridge the sim-to-real gap, we implement a continuous closed-loop data assimilation mechanism; the pipeline tracks macroscopic deformations and free-surface fluid boundaries in real-time using deep segmentation networks combined with sparse optical flow, dynamically correcting the autoregressive simulation rollout and eliminating numerical drift. To test the validity of our approach, we demonstrate the extreme generalization capabilities of our approach across two disparate physical regimes: the large deformations of a viscoelastic beam and the non-linear sloshing of a viscous fluid. In both scenarios, the unified framework instantiates physically accurate simulations on novel, unseen geometries without case-specific retraining, operating well within real-time latency budgets (approximately 25 ms per frame) and enabling the direct projection of latent mechanical variables via Augmented Reality.

arXiv

AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use

Junzhi Chen, Harsh Trivedi, Jane Pan, Michael JQ Zhang, Tejas Srinivasan, Niranjan Balasubramanian, Ashish Sabharwal

Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.g., to ask clarification questions, prompt for confirmation, and inform the user when the instruction is infeasible. However, current benchmarks for evaluating agent-user interactions do not capture the diversity of such interactions. Further, they operate in small environments with few, often non-state-changing, APIs. To address this gap, we introduce AppWorld-UL, a ``user-in-the-loop'' benchmark of 516 challenging tasks requiring diverse agent-user interactions. Building upon the AppWorld framework with 9 popular simulated apps like Amazon and Spotify, we systematically modify original tasks to introduce ambiguities and constraints that necessitate various types of agent-user interaction. User behavior is simulated by an LLM prompted to respond with carefully designed knowledge boundaries, offering more reliable simulation than the unconstrained or overly rigid alternatives used in prior work. Our evaluation reveals that a state-of-the-art LLM, Claude Opus 4.7, achieves only 48.6% success on AppWorld-UL, and only 35.7% on the harder, compositional subset. On the stricter, scenario-level metric, compositional task performance drops to only 21.3%. Our analysis reveals that correct user-interaction is crucial for success. This demonstrates the benchmark's difficulty and its potential to advance research on user-in-the-loop tool-use agents.

arXiv

GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification

Md Faraz Kabir Khan, Saeed Anwar, Ghulam Mubashar Hassan

The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before. We introduce GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images (10 classes, 32$\times$32, 50k/10k split) generated using three architecturally diverse state-of-the-art models: FLUX.2-dev (Rectified Flow Transformer), HunyuanImage-3.0 (MoE Transformer), and Qwen-Image-2512 (Multimodal Diffusion Transformer), to advance research in AI-generated image detection. A central challenge in this domain is that detectors perform well on known generators but degrade on unseen ones. GenSyn10 addresses this limitation by curating data from multiple contemporary architectures under a standardized generation protocol, enabling controlled and systematic evaluation of out-of-distribution (OOD) generalization to novel generators. Images are generated using a template-based prompt engine and downsampled to ensure consistency. We evaluate 17 image classification models under a four-stage protocol: real-data baseline, zero-shot transfer, fine-tuning, and retention. Despite a measurable domain gap, CIFAR-10-trained models achieve up to 96.86\% zero-shot accuracy on GenSyn10, increasing to 99.88\% after fine-tuning. In binary real-vs-synthetic classification, fine-tuned models achieve 97-99.9\% accuracy on seen generators but drop to 79-96\% on images from an unseen generator, highlighting persistent limitations in OOD generalization. These results establish GenSyn10 as a controlled benchmark for studying synthetic image detection beyond single-generator settings, supporting research on robustness, domain adaptation, and cross-generator generalization.

arXiv

CMSL: Constructive Multi-Sequence Learning for Recommendation Systems

Zikun Cui, Renzhi Wu, Junjie Yang, Li Sheng, Jijie Wei, Linfeng Liu, Tai Guo, Tao Jia, Xiaodong Wang, Hong Li, Li Yu, Sri Reddy, Hong Yan

Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) by capturing the temporal nuances of user behavior. However, current state-of-the-art architectures operate under a limiting analogy: they treat user history as a monolithic chronological sequence like a sentence in a Large Language Model (LLM). We observe a fundamental divergence between natural language and recommendation data: unlike the linear, logical flow of text, user history is inherently multi-faceted. A user's journey is a fragmented reflection of diverse interests, resulting in much weaker coherence between items than is found in LLM training data. This lack of structural unity leads to context pollution. In single-sequence modeling, unrelated behaviors compete for the same attention budget. This "noisy" signal dilutes the model's focus, effectively capping its ability to discern high-intent patterns from background activity. To address this, we propose Constructive Multi-Sequence Learning (CMSL), a paradigm shift from passive sequence ingestion to active "context engineering" that constructs multiple coherent sequences in latent space. CMSL leverages a learnable Sequence Construction Module to disentangle user history into "pure" thematic strands, followed by a linear attention mechanism to efficiently model these strands at scale. CMSL has been deployed across ranking and retrieval tasks and across four major surfaces at Meta.

arXiv

Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs

Skatje Myers, Dmitriy Dligach, Timothy A. Miller, Samantha Barr, James Landefeld, Yanjun Gao, Matthew Churpek, Anoop Mayampurath, Majid Afshar

Objective: To evaluate whether retrieval-augmented generation (RAG) can serve as an efficient alternative to long-context prompting for clinical reasoning over electronic health records (EHRs). Methods: We defined three EHR-based tasks that are replicable across health systems and vary in reasoning complexity: 1) extracting imaging procedures (modality, date, and anatomic site), 2) generating timelines of therapeutic antibiotic use, and 3) identifying the key diagnoses for a hospitalization. Using real inpatient clinical notes from a US academic health system, we evaluated three large language models (GPT-5.4-mini, Mistral Medium 3, DeepSeek V3.1) with varying amounts of provided context, comparing targeted retrieval to using the most recent clinical notes. Results: For Imaging Procedures, RAG strongly outperformed recent-note inputs and exceeded long-context performance (by 0.17-9.83 F1 across all models) using fewer than 8K tokens. Similar benefits were observed for Antibiotic Timelines, where <8K of retrieved tokens matched long-context recent-notes performance (between -3.26 to +3.24 Jaccard). Error analysis revealed that missing information in the clinical notes--often due to inter-hospital transfers--limited performance to some extent. However, performance on the Diagnosis Generation task remains largely static across methods and models. Discussion: RAG demonstrated strong token efficiency across tasks, with the clearest and most consistent gains observed for imaging extraction and antibiotic timeline reconstruction. Diagnosis generation proved the most challenging task, suggesting ceiling effects imposed by documentation variability and evaluation constraints. Conclusion: Our results suggest that RAG remains a competitive and efficient approach for clinical tasks over large amounts of EHR, even as newer models become capable of handling increasingly longer amounts of text.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.