A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning
Jiali Cheng, Ziheng Chen, Chirag Agarwal, Hadi Amiri
AI conference papers
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.
Jiali Cheng, Ziheng Chen, Chirag Agarwal, Hadi Amiri
Adrian Brasoveanu, Jakub Dotlacil
The systematicity of natural language interpretation—our ability to understand novel expressions by compositionally combining familiar elements—has been central to debates about symbolic versus neural approaches to cognition since Fodor and Pylyshyn (1988). We investigate whether artificial neural networks can learn model-theoretic interpretation functions that generalize systematically to out-of-training-sample sentences, framing interpretation as an encoding task from discrete linguistic input to continuous truth-conditional representations. We extend Frank et al. (2009) with entity-level semantic representations, modern architectures (GRU, LSTM, Attention with AbsPE/RoPE), principled competing event generation, extended systematicity tests (∼350 vs. ∼80 sentences), and a two- dimensional difficulty analysis disaggregating results by modifier complexity. Across 140 trained models (7 architectures), we find that capacity-matched architectures perform comparably on easy tests, but gated recurrent networks (GRU and LSTM) significantly outperform transformer architectures on the hardest compositional generalization test (Basic Event), while ungated SRN does not—indicating that the gating mechanism is a critical factor. Entity vectors significantly improve scores on Basic Event across most architectures, with gated architectures benefiting most, validating formal semantics’ treatment of entities as important theoretical primitives. The extended test set reveals that systematicity difficulty has two dimensions: the type of systematicity test (as in Frank et al. 2009), and the number of modifiers being composed.
Rob van der Goot
A first decision for any automated natural language processing system is the granularity of the input units. Traditionally, characters or words have been used, but recently, subwords have become the standard. In this paper, we investigate trends in input processing steps and discuss common shortcomings in this foundational first step of model design. We start by providing an overview of currently used tokenizers, showing that there is only minimal variety, with three highly similar designs dominating current models, and many of the tokenizers being exact duplicates. Next, we reconsider Unicode normalization strategies. Previous work has recommended applying consistent normalization; however, we argue that this removes signal and we show how this can harm performance for language classification. Finally, we take a closer look at UTF-8 character encoding, the very first layer of representation used in many language models. We argue that UTF-8 is not optimized for efficiency, nor for fairness across languages, and propose proof of concept alternatives focused on fairness and efficiency. Based on our findings, we recommend future work to 1) put more thought into subword segmentation and explore more diversity, 2) apply normalization only when beneficial 3) consider alternative character encodings for models operating on the byte-level.
Quy-Anh Dang, Chris Ngo
Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but existing methods suffer from critical limitations: activation addition requires careful coefficient tuning and is sensitive to layer-specific norm variations, while directional ablation provides only binary control. Recent work on Angular Steering introduces continuous control via rotation in a 2D subspace, but its practical implementation violates norm preservation, causing distribution shift and generation collapse, particularly in models below 7B parameters. We propose Selective Steering, which addresses these limitations through two key innovations: (1) a mathematically rigorous norm-preserving rotation formulation that maintains activation distribution integrity, and (2) discriminative layer selection that applies steering only where feature representations exhibit opposite-signed class alignment. Experiments across nine models demonstrate that Selective Steering achieves 5.5 higher attack success rates than prior methods while maintaining zero perplexity violations and approximately 100% capability retention on standard benchmarks. Our approach provides a principled, efficient framework for controllable and stable LLM behavior modification.
Dasol Choi, Guijin Son, Hanwool Lee, Minhyuk Kim, Hyunwoo Ko, Teabin Lim, Eungyeol Ahn, Jungwhan Kim, Seunghyeok Hong, Youngsook Song
Current vision-language benchmarks predominantly feature well-structured questions with clear, explicit prompts. However, real user queries are often informal and underspecified. Users naturally leave much unsaid, relying on images to convey context. We introduce HAERAE-Vision, a benchmark of 653 real-world visual questions from Korean online communities (0.76% survival from 86K candidates), each paired with an explicit rewrite, yielding 1,306 query variants in total. Evaluating 39 VLMs, we find that even state-of-the-art models (GPT-5, Gemini 2.5 Pro) achieve under 50% on the original queries. Crucially, query explicitation alone yields 8 to 22 point improvements, with smaller models benefiting most. We further show that even with web search, under-specified queries underperform explicit queries without search, revealing that current retrieval cannot compensate for what users leave unsaid. Our findings demonstrate that a substantial portion of VLM difficulty stem from natural query under-specification instead of model capability, highlighting a critical gap between benchmark evaluation and real-world deployment.
Yuyu Liu, Sarang Rajendra Patil, Mengjia Xu, Tengfei Ma
Electronic health record (EHR) question answering is often handled by LLM-based pipelines that are costly to deploy and do not explicitly leverage the hierarchical structure of clinical data. Motivated by evidence that medical ontologies and patient trajectories exhibit hyperbolic geometry, we propose HypEHR, a compact Lorentzian model that embeds codes, visits, and questions in hyperbolic space and answers queries via geometry-consistent cross-attention with type-specific pointer heads. HypEHR is pretrained with next-visit diagnosis prediction and hierarchy-aware regularization to align representations with the ICD ontology. On two MIMIC-IV-based EHR-QA benchmarks, HypEHR approaches LLM-based methods while using far fewer parameters. Our code is publicly available at https://github.com/yuyuliu11037/HypEHR.
Elisabeth Kirsten, Jost Große Perdekamp, Qinyuan Wu, Mihir Upadhyay, Krishna P. Gummadi, Muhammad Bilal Zafar
The advent of LLMs has given rise to generative search, a new search paradigm in which LLMs retrieve information from the web related to a query and synthesize it into a single, coherent response. This paradigm differs fundamentally from traditional web search, where results are returned as a ranked list of independent web pages. In this paper, we ask: Along what dimensions does generative search differ from traditional search?We conduct a systematic comparison between Google organic search and five generative search systems from three providers: Google, OpenAI, and Perplexity. Our analysis reveals substantial variation among engines in their reliance on internal v.s. external knowledge, source diversity, and stability. While generative systems often achieve topical coverage comparable to traditional search, they do so using markedly different retrieval footprints and synthesis strategies. We further show that the outputs of generative search can vary across time and executions, raising new challenges for robustness. Our findings demonstrate that generative search introduces new dimensions that are not captured by existing evaluation paradigms, motivating the development of evaluations that explicitly account for retrieval behavior, synthesis, and stability in generative search systems.
Xinyu Zhao, Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Jiarui Sun, Yan Zheng, Mahashweta Das, Tianlong Chen
While memory is a core component in agent systems, its behavioral impact in complex, long-horizon domains like machine learning engineering (MLE) remains poorly understood. Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success. This paper presents a systematic study dissecting how memory influences agent behavior and performance across diverse MLE challenges. We first introduce a dynamic coding memory designed to capture and reuse debugging experiences, and integrate it into two representative agent paradigms: a sequential, chain-based agent that mirrors human-like iterative refinement, and a parallel, tree-based agent that performs broad, self-exploratory search in the code space. Our central finding is that the role of memory is contingent on the agent’s underlying architecture. For chain-based agents, memory proves highly beneficial, enabling them to avoid recurring mistakes and engage in more coherent, iterative refinement, which significantly improves reliability and task success. In contrast, for tree-based search agents, memory introduces a critical trade-off: it enhances procedural stability at the cost of constraining search diversity, which can prematurely narrow exploration and lead to suboptimal final solutions. These findings reveal a fundamental trade-off between procedural reliability and solution innovation modulated by memory, offering insights for designing more effective and robust MLE agents.
Hieu Tran, Zonghai Yao, Hong Yu
Reinforcement learning has shown strong promise for strengthening the reasoning ability of large language models (LLMs), but sparse, delayed rewards over long chains make token-level credit assignment a central challenge. Actor–critic methods like PPO provide token-level credit but require training a value network alongside the policy, which introduces complexity and can encourage overfitting. Critic-free alternatives such as GRPO avoid this burden but rely on sequence-level outcomes, distributing a single reward uniformly across tokens and ignoring structural differences between responses. We propose Prefix-to-Tree (P2T), which organizes the sampled responses of a prompt into a prefix tree and computes nonparametric prefix values by aggregating descendant outcomes. Building on this idea, we develop TEMPO (Tree-Estimated Mean Prefix Value for Policy Optimization), a critic-free algorithm that enriches GRPO with branch-aware temporal-difference (TD) corrections. Across Qwen3-1.7B and Qwen3-4B, TEMPO consistently improves both convergence and final performance over PPO and GRPO on in-distribution benchmarks (MATH, MedQA) and out-of-distribution settings (GSM-HARD, AMC23, MedMCQA, MMLU-Medical), achieving higher validation accuracy within comparable wall-clock time.
Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng
We introduce FinWorkBench (a.k.a. Finch) for evaluating AI agents on real-world, enterprise-grade finance and accounting workflows that interleave data entry, structuring, formatting, web search, cross-file retrieval, calculation, modeling, validation, translation, visualization, and reporting. Finch is sourced from authentic enterprise workspaces from Enron (15,000 files and 500,000 emails) and other financial institutions, covering the period 2000–2025 and preserving the in-the-wild messiness of multimodal artifacts such as tables and charts across diverse domains including budgeting, trading, asset management, and operational management.We propose a workflow construction process that combines LLM-assisted mining of workflows from authentic enterprise environments with expert annotation: (1) LLM-assisted, expert-verified derivation of workflows from real-world email threads and spreadsheet version histories, and (2) meticulous annotation requiring over 700 hours of expert effort. This yields 172 composite workflows with 384 tasks, involving 1,710 spreadsheets with 27 million cells, along with PDFs and other artifacts, capturing the intrinsically messy, long-horizon, knowledge-intensive, and collaborative nature of real-world enterprise work.We conduct both human and automated evaluations of frontier AI systems, including GPT 5.1, Claude Sonnet/Opus 4.5, Gemini 3 Pro, Grok 4, and Qwen 3 Max. Under human evaluation, GPT 5.1 Pro spends an average of 16.8 minutes per workflow yet passes only 38.4% of workflows. Comprehensive case studies further surface the challenges that real-world enterprise workflows pose for AI agents.
Jun Zhuang, Chaowen Guan
In the era of noisy intermediate-scale quantum (NISQ) computing, Quantum Neural Networks (QNNs) have emerged as a promising approach for various applications, yet their training is often hindered by barren plateaus (BPs), where gradient variance vanishes exponentially as the qubit size increases. Most initialization-based mitigation strategies rely heavily on pre-designed static parameter distributions, thereby lacking adaptability to diverse model sizes or data conditions. To address these limitations, we propose AdaInit, a foundational framework that leverages large language models with the submartingale property to iteratively synthesize initial parameters for QNNs that yield non-negligible gradient variance, thereby mitigating BPs. Unlike conventional one-shot initialization methods, AdaInit adaptively explores the parameter space by incorporating dataset characteristics and gradient feedback, with theoretical guarantees of convergence to finding a set of effective initial parameters for QNNs. We provide rigorous theoretical analyses of the submartingale-based process and empirically validate that AdaInit consistently outperforms existing initialization methods in maintaining higher gradient variance across various QNN scales. We believe this work may initiate a new avenue to mitigate BPs.
Mian Zhang, Shaun M. Eack, Zhiyu Chen
Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle to consistently provide effective responses to client speeches, largely due to the lack of supervision from high-quality real psycho-counseling data, whose content is typically inaccessible due to client privacy concerns. Furthermore, the quality of therapists’ responses in available sessions can vary significantly based on their professional training and experience. Assessing the quality of therapists’ responses remains an open challenge. We address these challenges by first proposing a set of professional and comprehensive principles to evaluate therapists’ responses to client speeches. Using these principles, we create a Psycho-Counseling Preference dataset, PsyCoPref, which contains 36k high-quality preference comparison pairs. This dataset aligns with the preferences of professional psychotherapists, providing a robust foundation for evaluating and improving LLMs in psycho-counseling. Experiments on reward modeling and preference learning demonstrate that PsyCoPref is an excellent resource for LLMs to acquire essential skills for responding to clients in a counseling session. Our best-aligned model achieves an impressive win rate of 87% against GPT-4o.
Pei-Fu Guo, Ya An Tsai, Chun-Chia Hsu, Kai-Xin Chen, Yun-Da Tsai, Kai-Wei Chang, Nanyun Peng, Mi-Yen Yeh, Shou-De Lin
While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require understanding distributional information, such as population-level trends and preferences expressed across collections of text. We introduce Text2DistBench, a reading comprehension benchmark for evaluating LLMs’ ability to infer distributional knowledge from natural language. Built from real-world YouTube comments about movie and music entities, the benchmark provides models with entity metadata and associated comments, and requires them to answer distributional questions, such as estimating the proportions of positive and negative comments, or identifying the most and second most frequent topics discussed among viewers. To support reliable and long-term evaluation, the construction pipeline of Text2DistBench is fully automated and continuously updated to incorporate newly emerging entities over time. Experiments across multiple LLMs show that while models substantially outperform random baselines, performance varies widely across different distribution types and characteristics. These findings highlight both the capabilities and limitations of current LLMs in distributional reading comprehension and demonstrate the value of Text2DistBench as a practical and scalable testbed for future research.
Yibo Peng, Peng Xia, Ding Zhong, Kaide Zeng, Siwei Han, Yiyang Zhou, Jiaqi Liu, Ruiyi Zhang, Huaxiu Yao
Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely read text embedded in images, or do they merely rely on parametric shortcuts in the text prompt? In this work, we diagnose this issue by introducing the Visualized-Question (VQ) setting, where text queries are rendered directly onto images to structurally mandate visual engagement. Our diagnostic experiments on Qwen2.5-VL reveal a startling capability-utilization gap: despite possessing strong OCR capabilities, models suffer a performance degradation of up to 12.7% in the VQ setting, exposing a deep-seated modality laziness. To bridge this gap, we propose SimpleOCR, a plug-and-play training strategy that imposes a structural constraint on the learning process. By transforming training samples into the VQ format with randomized styles, SimpleOCR effectively invalidates text-based shortcuts, compelling the model to activate and optimize its visual text extraction pathways. Empirically, SimpleOCR yields robust gains without architectural modifications. On four representative OOD benchmarks, it surpasses the base model by 5.4% and GRPO based on original images by 2.7%, while exhibiting extreme data efficiency, achieving superior performance with 30x fewer samples (8.5K) than recent RL-based methods. Furthermore, its plug-and-play nature allows seamless integration with advanced RL strategies like NoisyRollout to yield complementary improvements. Code is available at https://github.com/aiming-lab/SimpleOCR.
Varshini Reddy, Craig W. Schmidt, Seth Ebner, Adam Wiemerslage, Yuval Pinter, Chris Tanner
Large language models (LLMs) have achieved impressive proficiency in basic arithmetic, rivaling human-level performance on standard numerical tasks. However, little attention has been given to how these models perform when numerical expressions deviate from the prevailing conventions present in their training corpora. In this work, we investigate numerical reasoning across a wide range of numeral scripts and formats. We show that LLM accuracy drops substantially when numerical inputs are rendered in underrepresented scripts or formats, despite the underlying mathematical reasoning being identical. We further demonstrate that targeted prompting strategies, such as few-shot prompting and explicit numeral mapping, can greatly narrow this gap. Our findings highlight an overlooked challenge in multilingual numerical reasoning and provide actionable insights for working with LLMs to reliably interpret, manipulate, and generate numbers across diverse numeral scripts and formatting styles.
Xinyu Zhao, Kangqi Ni, Jie Peng, Ang Li, Tianlong Chen
Multimodal Large Language Models (MLLMs) show strong potential for cross-modal understanding by integrating powerful language models with multimodal encoders. However, extending MLLMs to handle a diverse range of modalities introduces two critical and intertwined challenges: (1) the reliance on fully paired multimodal data, often scarce or costly to acquire across all modalities, and (2) the computational inefficiency from processing numerous modality tokens and requiring substantial model updates for each new modality. To address these challenges, we enable MLLMs to handle missing modalities by generating representations for absent inputs. Furthermore, recognizing that an increasing number of modalities leads to linearly scaling token counts and that lengthy generated sequences can hinder performance, we employ a dual-stage compression mechanism. It first reduces the number of tokens per modality and then condenses information from multiple modalities into a single, compact token sequence. This culminates in Flex-M^3, a novel MLLM framework designed for flexible and efficient learning across arbitrary combinations of modalities. Experiments across diverse multimodal benchmarks and backbones demonstrate that Flex-M^3 robustly handles varied modality inputs and scales efficiently. Notably, Flex-M outperforms its counterpart trained on only full-modality data, with consistent improvements of 2.29%, 3.15%, 11.01% on multimodal reasoning tasks NExT-QA, MUSIC-AVQA, SQA3D. Moreover, Flex-M^3 demonstrates superior robustness during inference, even when a high proportion of modalities are missing from the input samples, showcasing its capacity for complex, data-scarce multimodal applications.
Vishal Pramanik, Maisha Maliha, Nathaniel D. Bastian, Alvaro Velasquez, Susmit Jha, Sumit Kumar Jha
Chain-of-thought (CoT) prompting makes language models write step-by-step explanations, but these steps may not match what the model actually used to choose its answer. Existing faithfulness checks often only test whether changing the written chain changes the answer, without verifying whether the steps are truly supported by the given evidence, or they require special prompts that do not generalize well. We present NSF-CoT, a neuro-symbolic formal verification method that checks CoT faithfulness step by step for contextual question answering. NSF-CoT (1) converts the provided context facts and each reasoning step into simple logical statements, (2) uses counterfactual attribution to estimate which context facts the model relied on while generating each step, and (3) verifies each step using a hybrid checker that combines an SMT solver with an LLM-based entailment judge. For every step, we score groundedness (supported by the full context), validity (supported by the facts the model relied on), and utility (helps reach the final answer), and combine them into a faithfulness score. Across OpenBookQA, QASC, and HotpotQA, NSF-CoT consistently outperforms causal mediation, perturbation probes, and behavioral monitoring, and it identifies reasoning steps that are not only unfaithful but also harmful to the model’s final decision.
Hang Wang, Utkarsh Garg, Reza Davari, Huitian Jiao, Hao Cheng, Baolin Peng, Si-Qing Chen, Tao Ge
Large language models increasingly power AI agents for tasks requiring iterative refinement: document editing demands targeted revisions while preserving cross-references, code refactoring requires tracking function dependencies, and knowledge base updates cascade through related entities. Iterative editing with AI agents faces a fundamental efficiency-consistency tradeoff: maintaining consistency requires full-context awareness of dependencies, but processing entire documents for each edit incurs prohibitive token costs and latency. Isolated edits improve efficiency but risk breaking cross-references and violating semantic constraints. We introduce LEDGER (scaLing Agentic document editing with Dependency-aware Graph rEtRieval), a framework that constructs lightweight dependency graphs capturing semantic relationships and structural hierarchies across document elements. For each edit, graph traversal identifies affected elements and retrieves only necessary context. Experiments across 1,900 test cases spanning six state-of-the-art models show LEDGER achieves 76 consistency versus 56 baseline while reducing token usage by 85 . Critically, LEDGER with low reasoning effort matches baseline performance at high reasoning effort using 70 fewer tokens, suggesting explicit dependency representations can substitute for expensive internal reasoning with implications for agentic systems operating on structured data.
Inderjeet Jayakumar Nair, Lu Wang
Evaluations of LLMs’ ethical risks and value inclinations often rely on short-form surveys and psychometric tests, yet real-world use involves long-form, open-ended responses—leaving value-related risks and preferences in practical settings largely underexplored. In this work, we ask: Do value preferences inferred from short-form tests align with those expressed in long-form outputs? To address this question, we compare value preferences elicited from short-form reactions and long-form responses, varying the number of arguments in the latter to capture users’ differing verbosity preferences. Analyzing five LLMs (llama3-8b, gemma2-9b, mistral-7b, qwen2-7b, and olmo-7b), we find (1) a weak correlation between value preferences inferred from short-form and long-form responses across varying argument counts, and (2) similarly weak correlation between preferences derived from any two distinct long-form generation settings. (3 Alignment yields only modest gains in the consistency of value expression. Further, we examine how long-form generation attributes relate to value preferences, finding that argument specificity negatively correlates with preference strength, while representation across scenarios shows a positive correlation. Our findings underscore the need for more robust methods to ensure consistent value expression across diverse applications.
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Proxy optimization, where AI systems exploit evaluator weaknesses rather than improve intended objectives, threatens both reinforcement learning (reward hacking) and LLM alignment (evaluator gaming). We introduce the Evaluator Stress Test (EST), an invariance-based framework that detects proxy gaming by separating exploitable sensitivity (e.g., format, physics bugs) from content-driven improvements using controlled perturbations with semantic validity audits. We validate EST across both domains. In RL, across 15 environments and 5 algorithms (2,156 expert-annotated episodes), EST achieves 78.4% precision and 81.7% recall. In LLM alignment, across 4 tasks, 2 model scales, 2 training methods, and 2 judges (1,200 human-annotated instances), EST achieves 74.2% precision and 78.6% recall with early warning signals preceding quality decline. Cross-domain analysis reveals that proxy-true correlation tracking transfers directly between domains, while perturbation design requires domain adaptation. Closed-loop mitigation improves human win-rate by 8.3 points (LLM) and reduces hacking by 54.6% (RL). We release benchmarks for both domains: 2,156 RL episodes and 1,200 LLM instances.
Keep browsing
30+ top conferences, by conference, year, and topic.
Open any conference and year for its full paper list.
All conferences →Search 210,000+ papers by title, author, or keyword.
Search papers →