paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

POLARIS: Guiding Small Models to Write Long Stories

Rishanth Rajendhran, Jenna Russell, Mohit Iyyer, John Frederick Wieting

Small open-weight models struggle at long-form creative writing: their generated stories either fall far short of the requested length, or their quality significantly degrades as length increases, especially when compared to frontier models. We present POLARIS (Policy Optimization with LLM-as-a-judge rewards and Anchored-Reference Injection for Storywriting), a lower-compute GRPO recipe with two key ingredients: a frontier LLM judge with a structured Story Quality rubric as the online reward, and human-reference injection (HRI), where a teacher-forced human-written story serves as a high-reward anchor within each GRPO group. By applying our training recipe to Qwen3.5-9B, using a dataset of approximately 1.4K prompt-story pairs derived from 100 short-story anthologies and 4 A100 GPUs, we obtain POLARIS-9B. Across five benchmarks spanning in-distribution and out-of-distribution prompts and rubrics, POLARIS-9B is competitive with much larger open-weight models while following length instructions more closely. A blinded human evaluation confirms that POLARIS-9B is preferred to the base Qwen3.5-9B and on par with Qwen3.5-27B. Despite training only on stories up to 4k words, POLARIS-9B preserves quality on prompts requesting stories up to 3 times the training length, a regime where most open-weight models degrade substantially in quality, length adherence, or both. More broadly, our results suggest that length generalization is a meaningful stress test for creative-writing models and a useful lens for distinguishing otherwise close models.

arXiv

Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

Yu Xia, Zhouhang Xie, Xin Xu, Byungkyu Kang, Prarit Lamba, Xiang Gao, Julian McAuley

Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Existing efficient reasoning methods control thinking length by shortening, early-stopping, or compressing traces, leaving how the model thinks implicit. In this paper, we propose Agentic Chain-of-Thought Steering (ACTS), which formulates reasoning steering as a Markov decision process where a controller agent adaptively steers a frozen reasoner during inference. At each step, the controller observes the reasoning trace and remaining thinking budget, then issues a steering action consisting of a reasoning strategy and a steering phrase that initiates the next reasoner step. This enables budget-aware strategy control for efficient reasoning while preserving the reasoner's generation continuity. We initialize the controller agent from our constructed synthetic steering trajectories with multi-budget augmentation, and further optimize it via reinforcement learning with budget-conditioned reward shaping. Experiments across multiple benchmarks show that ACTS achieves competitive accuracy with substantial token savings, and enables controllable accuracy-token trade-offs across different reasoners and tasks. The code is available at https://github.com/Andree-9/ACTS.

arXiv

Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings

Clara Haya Suslik, Or Shafran, Mor Geva

As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for safety and compliance. Prominent methods seek persistent removal by updating the model's parameters, yet the target knowledge often can be recovered through adversarial prompting or relearning. In this work, we hypothesize this limitation stems in part from existing methods overlooking the embedding layer. To address this, we introduce EMBedding ERasure (EMBER), a plug-n-play erasure module that leverages Sparse Matrix Factorization for precise erasure of concept-related features from token embeddings. Through comprehensive evaluations across diverse concepts on Gemma-2-2B-it and Llama-3.1-8B-Instruct, we find that augmenting existing methods with EMBER consistently improves erasure efficacy and specificity across task formats, with minimal coherence loss. Moreover, it dramatically improves robustness to relearning, reducing regained accuracy by up to 50%, limiting it to 35% on Llama compared to 70%-76% for prior methods. Further analysis shows that the coherence cost is localized, affecting only a small set of concept-exclusive tokens. Our work establishes that precise embedding-level intervention is necessary for robust concept erasure, and demonstrates that existing methods can benefit from such augmentation.

arXiv

Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment

Hamidreza Hasani Balyani, Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi, Amin Gholami Davodi, Arshia Gharagozlou

Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sales assistants for purchases. Whether they stay truthful when honesty conflicts with their own payoff is a core alignment question. We turn the canonical Crawford-Sobel cheap-talk model into a pre-specified benchmark for LLM honesty under preference misalignment, in which theory supplies an exact oracle. A sender observes a state omega in [0,1], wants the receiver's action near omega+b, and sends one costless message to a receiver whose ideal action is omega. For the positive-bias grid b in {0.01,0.04,0.08,0.12} the exact most-informative partition sizes are 7,4,3,2, with oracle normalized mutual information 0.5294, 0.3268, 0.2205, 0.1829. Extending a pre-registered 4-model run of 12,000 sender calls to eight models across two capability tiers and 39,569 logged calls, all models over-reveal relative to the most-informative equilibrium by 1.8 to 4.5x: pooled normalized mutual information stays at 0.82-0.96 where the oracle prescribes 0.18-0.53. Informativeness declines with bias as predicted (beta = -1.71, t = -7.50) but never approaches the strategic optimum; rather than coarse partitions, models show near-full revelation with a constant upward offset tracking their bias (linear exaggeration). A structural hint separates capability from propensity: told the equilibrium partition size, reasoning models state a correct Crawford-Sobel cell in 0.20-0.99 of messages while the non-reasoning tier never exceeds 0.005. The capability is present but goes unexercised unless asked for, locating the failure in propensity rather than competence. A decoder ablation shows the finding is recoverable only when the receiver reads the sender's stated number: an embedding-only decoder mis-reads the same data as near-babbling.

arXiv

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention

Dong Le, Thong Nguyen, Cong-Duy Nguyen, Anh Tuan Luu

Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tasks. Existing remedies act on the write side of memory through gating, delta updates, or kernel feature maps, but the read step is left unchanged: every past key contributes additively to the output, so useful targets are diluted by the bulk of stored vectors. We borrow one specific piece of softmax's geometry to construct a cheap read-time contraction of the query. A second-order Taylor expansion of the softmax log-partition at the isotropic-attention point gives a local quadratic model whose curvature coincides with the running key covariance, a quantity that can be maintained with the same recurrent/chunkwise mechanism as the linear-attention state. The associated linear operator contracts the query along the high-variance directions of memory before it reads the state. We call this mechanism Curvature-Conditioned Query (CCQ). CCQ modifies only the read step and is composable with any linear-attention backbone. Attached to GLA and Gated DeltaNet, it improves perplexity, zero-shot downstream accuracy, S-NIAH retrieval at and beyond the training context, length-extrapolation perplexity from 4K to 20K, and LongBench accuracy.

arXiv

Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues

Zhangqi Duan, Shuyan Huang, Alexander Scarlatos, Jaewook Lee, Simon Woodhead, Andrew Lan

A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as students, which can facilitate tutor model evaluation and training. Existing work mostly focuses on within-dialogue simulation, which lacks context on student knowledge and behavior, partly due to not grounding in past student question-answering or dialogue interactions. In this work, we introduce the task of history-conditioned student simulation, where the goal is to accurately predict student dialogue turns by leveraging information in the student's learning history. We propose a two-component framework in which a profile generator summarizes a student's history and a simulator predicts student turns conditioned on the resulting profile. We train both components with reinforcement learning (RL), yielding profiles optimized for faithful student simulation. We evaluate our method and baselines on the first-of-its-kind real-world dataset of student dialogues and question responses that we collect from a math learning platform. Extensive experiments show that our method significantly outperforms baselines, and demonstrate the importance of history, profiles, and RL training.

arXiv

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

Aditya Nawal, Manit Baser, Mohan Gurusamy

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines two axes: how retrieval is integrated into the agent pipeline and the properties of the retrieved content. Along the integration axis, we find that binding tool invocation and response generation in a single step amplifies harmful outputs. Along the content axis, we uncover the Safe Source Paradox: even oppositional or safety-oriented sources, such as pages containing warnings or risk disclaimers, can increase harmful compliance by an average of 25% compared to the no-retrieval baseline. Finally, we show that relevance acts as a shared activation condition for both vulnerabilities. Similar patterns appear on frontier closed models, and harmful compliance remains elevated under several representative pipeline interventions, with some agents also entering this regime under autonomous retrieval. Because relevance is also what makes retrieval useful, these results expose a safety-utility trade-off for retrieval-enabled agents. We introduce HarmURLBench, a benchmark containing 1,405 real-world URLs paired with 320 harmful behaviors to support future evaluations.

arXiv

Why We Need Speech to Evaluate Speech Translation

Maike Züfle, Danni Liu, Vilém Zouhar, Jan Niehues

Speech translation models are increasingly capable of preserving speech-specific information (e.g., speaker gender, prosody, and emphasis), yet evaluation metrics remain blind to such phenomena. We meta-evaluate both text- and speech-based quality estimation metrics on two contrastive datasets targeting gender agreement and prosody, and find that both fall short, even when given direct access to the speech signal. We then train SpeechCOMET, a family of quality estimation models with speech encoders, and evaluate a state-of-the-art SpeechLLM as a judge. Both match or exceed text-based COMET on standard quality estimation, but neither consistently assesses speech-specific phenomena. We identify three causes: (1) speech-specific features are not reliably preserved in current encoders, (2) models tend to ignore the speech source signal, and (3) quality estimation training data contains too few relevant examples. We release all models and code, and argue that progress requires dedicated speech-specific training data and models that genuinely condition on speech.

arXiv

KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs

Haechan Kim, Seungjun Chung, Inkyu Park, Jihoo Lee, Jonghyun Lee

Speech language models (SpeechLMs) have achieved substantial progress by extending large language models (LLMs) to the speech modality. However, SpeechLM evaluation remains heavily centered on English, limiting reliable assessment of multilingual speech capabilities. Straightforward benchmark transfer through ASR, translation, normalization, and TTS can corrupt language-specific instructions, answer constraints, and spoken forms; for audio understanding, transferring source-language audio also fails to preserve target-language speaker attributes, accents, and paralinguistic properties. To address these limitations, we propose two human-agent benchmark-construction frameworks: one transfers source-language SpokenQA benchmarks into target-language SpokenQA benchmarks, and the other converts target-language ASR corpora into audio understanding benchmarks using transcriptions and speaker metadata. Using these frameworks, we construct and publicly release three Korean speech benchmarks: KVoiceBench and KOpenAudioBench for Korean SpokenQA, and KMMAU for Korean audio understanding, comprising 12,345 samples in total. We evaluate eight recent SpeechLMs and find that English-Korean performance gaps vary substantially across models and task families, and that SpokenQA and audio understanding rankings diverge, revealing complementary weaknesses invisible to English-only evaluation.

arXiv

MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation

Haoyu Zheng, Yun Zhu, Shu Yuan, Shangming Chen, Qing Wang, Wenqiao Zhang, Jun Xiao, Yueting Zhuang

Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to self-contamination: intermediate assistant replies enter later context and carry early deviations forward. Motivated by this mechanism, we propose MAIGO, an on-policy self-distillation method that reduces this contamination using history-cleaned references from the model's own policy. For middle turns, MAIGO removes prior assistant replies while preserving the user-visible sharded prefix; for answer turns, it distills from paired full-view references conditioned on the completed user-side dialogue. A reliability weight downweights middle-turn samples that disagree with the clean reference. MAIGO requires no verifier rewards, state labels, or inference-time scaffolding. Under the LiC paired-view protocol with deterministic verifiers, MAIGO improves Qwen2.5-7B-Instruct SHARDED accuracy from 52.8 to 66.1 and the SHARDED/FULL ratio from 66.5% to 84.1%, while keeping FULL accuracy within 2.3 points. These results show that self-contamination is a trainable component of the LiC gap.

arXiv

When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection

Zhengyu Hu, Zheyuan Xiao, Linxin Song, Fengqing Jiang, Yuetai Li, Zhihan Xiong, Yue Liu, Junhao Lin, Yao Su, Lijie Hu, Kaize Ding, Teng Xiao, Radha Poovendran

LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the highest-performing teacher to generate student training data, implicitly treating teacher test performance as a proxy for teaching quality. We show that this assumption can fail: even when multiple teachers provide correct answers to the same question, the answer from the strongest teacher is not necessarily the best supervision for a given student. To address this gap, we propose Student-Centric Answer Sampling (SCAS), a framework that selects from verified teacher-generated answers according to their estimated student-centric learning cost. Motivated by a token-wise gradient decomposition, we derive an efficient forward-only proxy for this cost and use it to guide answer selection during training. Experiments across 30 teacher models, 6 student base models, and 6 tasks show that SCAS consistently improves student performance, suggesting that effective distillation should prioritize supervision matched to the current student rather than teacher strength alone.

arXiv

Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification

Jingxi Qiu, Zeyu Han, Cheng Huang

Evidence absence is not evidence insufficiency, but fact verification benchmarks can make them observationally similar. The Not Enough Information (NEI) label is often operationalized through constructed evidence conditions, and that choice silently determines what a verifier learns. We introduce NEI-CAP, a construction-aware diagnostic protocol for insufficient-evidence evaluation. Each NEI example carries the construction family that produced it; NEI-CAP audits shortcut cues, validates hard cases through human adjudication, and tests whether competence transfers across constructions. We instantiate the protocol on SciFact, with FEVER and HoVer as bounded external controls. Across these settings, NEI competence does not transfer reliably: encoder verifiers and an instruction-tuned decoder trained on shortcut-prone constructions fail to recognize semantically related insufficient evidence, and mixed-construction training narrows but does not close the gap. Fixed-claim diagnostics further show that the evidence condition shifts confidence in the reference Support/Refute label, not only NEI recall, so an aggregate NEI score can hide which problem a model has actually solved. We therefore recommend reporting the construction family alongside the score, and distill the results into a checklist for benchmarks that carry an insufficient-evidence label.

arXiv

Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use

Tianda Sun, Dimitar Kazakov

We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation verbs over Complex WebQuestions. Under a self-verifiable retrieval reward, the policy's tool-grounded answer rate climbs from $3.8\%$ to $9.6\%$ over 250 steps, then collapses to $0\%$ within a single 50-step window -- a \emph{peak-then-collapse} pattern replicated across four seeds. Across seven reward designs, we find four recurring failure modes: adding denser or more targeted proxy rewards shifts the failure mode rather than eliminating it. We argue that a key difference from Python interpreters, web search, and JSON APIs is interface feedback: their failures often leak natural-language signal the model saw in pretraining. A Python traceback names the failing line; an empty Freebase result \texttt{[]} does not. Stripping away that surface exposes a degradation regime that same-family reward redesigns do not fix. A direct oracle ablation rules out relation selection: injecting gold relations at every retrieval call lifts exact-match accuracy by only $+0.20$~pp, and $95.4\%$ of retrieval-dependent errors are retrieval-composition failures rather than answer-extraction failures. As a mitigation, one-iteration self-distillation reaches $40.0\%$ EM at 7B and is capacity-invariant: doubling capacity to 14B improves EM by only $0.25$~pp, and initialization barely matters -- the ceiling appears interface-bound within the 7B--14B range tested.

arXiv

How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework

Björn Nieth, Marianna Gracheva, Michaela Mahlberg, Bjoern Eskofier, Emmanuelle Salin

While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of how human-like generated texts are on a linguistic level has been underexplored. From a corpus-linguistic perspective, language production is inherently context-dependent, with distinct communicative contexts giving rise to differences in frequencies and co-occurrence patterns of linguistic features. A text failing to adhere to these patterns can be content-wise correct, but still be unfavorable to human readers. In this work, we propose a context-aware evaluation framework in which human-likeness is assessed using a two-sample problem between the linguistic feature distribution of a human reference corpus for a given register and a corresponding LLM-generated corpus. We implement this framework using the Maximum Mean Discrepancy (MMD) and the 67 lexico-grammatical features introduced by Biber, which are commonly applied in corpus linguistics. In our experiments, we compare seven instruction-tuned, open-source models across five English-language datasets spanning distinct registers against a human baseline. While across all tested setups, LLMs deviate from the human baseline, which models are closest to human language depends on the register and is not dictated by model size.

arXiv

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

Shijie Lian, Bin Yu, Xiaopeng LIN, Zhaolong Shen, Laurence Tianruo Yang, Yurun Jin, Haishan Liu, Changti Wu, Hang Yuan, Cong Huang, Kai Chen

Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines

arXiv

OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling

Yuxuan Lou, Yang You

Muon fixes the \emph{direction} of every matrix-valued update at the polar factor of its momentum, while each layer's step \emph{magnitude} is addressed only by a static shape correction. We derive a dynamic per-layer scalar by adapting the LARS/LAMB trust-ratio principle to the orthogonalized setting, where the standard denominator candidates---the raw momentum norm or the polar-factor norm---either live in the wrong unit space or carry no update-scale information. The resulting method, \emph{OrScale}, uses the norm of the parameter-space direction actually applied and anchors each layer's ratio at one via a per-layer calibration, so that the Moonlight recipe (tuned for AdamW, shared with Muon via RMS matching) transfers with \emph{no additional sweep}; a component ablation confirms each design choice is individually load-bearing. Theoretically, OrScale retains a nuclear-norm $O(1/\sqrt{T})$ convergence rate for any clipped multiplier and achieves a strict layer-adaptive descent gain $κ_{\mathrm{eff}}>1$ under two conditions estimable from standard training diagnostics---a bound that predicts the gain should \emph{grow with architectural heterogeneity}. Experiments confirm the prediction: with every hyperparameter inherited verbatim from the Moonlight recipe, OrScale matches or beats Muon+Moonlight across dense 125M--1.1B FineWeb-Edu pre-training, and on a 16B-A3B mixture-of-experts model---where the logged trust ratios separate cleanly by layer class---the gap widens by an order of magnitude to $0.130$ nats ($3.8\%$ relative) at parity wall-clock cost.

arXiv

Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

Aishik Mandal, Hiba Arnaout, Clarissa W. Ong, Juliet Bockhorst, Kate Sheehan, Rachael Moldow, Tanmoy Chakraborty, Iryna Gurevych

Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling, but adapting them to this safety-critical domain is hindered by limited real-world data due to privacy constraints. Synthetic datasets provide a promising alternative, but existing approaches often rely on unstructured or semi-structured text inputs and overlook structural dependencies between a client's cognitive, emotional, and behavioral states, leading to psychologically inconsistent and less realistic interactions. We introduce Graph2Counsel, a framework for generating synthetic counseling sessions grounded in Client Psychological Graphs (CPGs) that encode relationships among clients' thoughts, emotions, and behaviors. Graph2Counsel uses a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT and Multi-Agent Feedback. It produces 760 sessions from 76 CPGs across diverse client profiles. In expert evaluation, our dataset outperforms prior datasets on specificity, counselor competence, authenticity, conversational flow, and safety (Krippendorff's $α$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on several metrics on CounselingBench and CounselBench, while matching baselines on others. We further introduce Therapy-Eval, a multi-turn evaluation framework, and demonstrate the effectiveness of our fine-tuned model in realistic therapeutic conversations. We make our code, data and fine-tuned model public.

arXiv

A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification

Joe Stacey, Hadas Orgad, Kentaro Inui, Benjamin Heinzerling, Nafise Sadat Moosavi

Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation, motivating a growing interest in efficient probe-based approaches. Yet it remains unclear how robust existing methods are, with prior work reporting conflicting conclusions under substantially different evaluation settings. We address this by introducing ProbeDrift, a systematic evaluation framework for supervised uncertainty probes covering a wide range of OOD settings across models, tasks, and distributional shifts. Using ProbeDrift, we train over 2,000 probes to disentangle the effect of key design choices, showing poor robustness of current methods beyond near-OOD settings. We find that robustness is driven by design decisions that have a largely invisible effect in-distribution, including the choice of feature type, aggregation strategy, and training signal. We argue that robust uncertainty estimation requires robust evaluation. To support this, we release ProbeDrift as a lightweight Python library that contains the train and test splits underpinning our extensive evaluation. We also show how insights from our evaluation can directly lead to more robust methods through a simple Hybrid Back-Off (HBO) strategy.

arXiv

Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs

Mengdan Zhu, Senhao Cheng, Liang Zhao

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to extract semantics in multi-step reasoning. We propose "Decompose, Look, and Reason" (DLR), a reinforced latent reasoning framework that dynamically decomposes queries into textual premises, extracts premise-conditioned continuous visual latents, and deduces answers through grounded rationales. We introduce a three-stage training pipeline and propose a novel Spherical Gaussian Latent Policy, to enable effective exploration in the latent space. Extensive experiments on vision-centric benchmarks show that DLR consistently outperforms strong baselines, including text-only, interleaved multimodal CoT, and latent reasoning methods, while providing superior stepwise interpretability.

arXiv

CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance

Haochen Liu, Weien Li, Rui Song, Zeyu Li, Chun Jason Xue, Xiao-Yang Liu, Sam Nallaperuma-Herzberg, Xue Liu, Ye Yuan

Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available evidence is internally inconsistent. Such a scenario exists in real-world healthcare settings, with patient-reported symptoms contradicting medical signs. To study this problem, we introduce MIMIC-DOS, a dataset for short-horizon organ dysfunction worsening prediction in the intensive care unit (ICU) setting. We derive this dataset from the widely recognized MIMIC-IV, a publicly available electronic health record dataset, and construct it exclusively from cases in which discordance between signs and symptoms exists. This setting poses a substantial challenge for existing LLM-based approaches, with single-pass LLMs and agentic pipelines often struggling to reconcile such conflicting signals. To address this problem, we propose CARE: a multi-stage privacy-compliant agentic reasoning framework in which a proprietary LLM provides guidance by generating structured categories and transitions without accessing sensitive patient data, while a local LLM uses these categories and transitions to support evidence acquisition and final decision-making. Empirically, under controlled retrospective evaluation on MIMIC-DOS, CARE achieves the best overall performance across key metrics among the evaluated LLMs and agentic workflows, showing that it can more robustly handle conflicting clinical evidence while preserving privacy.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →