{"total":84,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201,"area":"lr"},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199,"area":null},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2312.12241","title":"GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning","created":"2023-12-19","cited_by_count":108,"area":"lr"},{"id":"2310.10108","title":"On Generative Agents in Recommendation","created":"2023-10-16","cited_by_count":90,"area":"agents"},{"id":"2406.09170","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","created":"2024-06-13","cited_by_count":88,"area":"lr"},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"area":"lr"},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2402.11291","title":"Puzzle Solving using Reasoning of Large Language Models: A Survey","created":"2024-02-17","cited_by_count":45,"area":"lr"},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44,"area":"lr"},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2311.09731","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","created":"2023-11-16","cited_by_count":32,"area":null},{"id":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2406.09175","title":"ReMI: A Dataset for Reasoning with Multiple Images","created":"2024-06-13","cited_by_count":30,"area":"lr"},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28,"area":"lr"},{"id":"2403.16416","title":"How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendation","created":"2024-03-25","cited_by_count":27,"area":null},{"id":"2405.20131","title":"Language Models Need Inductive Biases to Count Inductively","created":"2024-05-30","cited_by_count":25,"area":null},{"id":"2309.04369","title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","created":"2023-09-08","cited_by_count":24,"area":null},{"id":"2412.15235","title":"OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models","created":"2024-12-12","cited_by_count":23,"area":"rag"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2408.10455","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","created":"2024-08-19","cited_by_count":22,"area":"agents"},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2311.00445","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","created":"2023-11-01","cited_by_count":20,"area":"lr"},{"id":"2501.01540","title":"BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery","created":"2025-01-02","cited_by_count":18,"area":null},{"id":"2407.03525","title":"UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2504.15800","title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","created":"2025-04-22","cited_by_count":17,"area":"rag"},{"id":"2410.07432","title":"Can Transformers Reason Logically? A Study in SAT Solving","created":"2024-10-09","cited_by_count":16,"area":"lr"},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2405.08035","title":"A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systems","created":"2024-05-13","cited_by_count":13,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2309.05452","title":"Evaluating the Deductive Competence of Large Language Models","created":"2023-09-11","cited_by_count":12,"area":null},{"id":"2410.13502","title":"MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2502.11176","title":"LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning","created":"2025-02-16","cited_by_count":12,"area":"lr"},{"id":"2502.08991","title":"Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2409.05197","title":"Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?","created":"2024-09-08","cited_by_count":10,"area":"lr"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2402.10735","title":"Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification","created":"2024-02-16","cited_by_count":9,"area":"lr"},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2311.00258","title":"Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis","created":"2023-11-01","cited_by_count":6,"area":"lr"},{"id":"2311.01230","title":"Multi-Operational Mathematical Derivations in Latent Space","created":"2023-11-02","cited_by_count":6,"area":null},{"id":"2501.00759","title":"Enhancing Transformers for Generalizable First-Order Logical Entailment","created":"2025-01-01","cited_by_count":6,"area":null},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2512.23511","title":"Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving","created":"2025-12-29","cited_by_count":6,"area":"lr"},{"id":"2407.08388","title":"On the attribution of confidence to large language models","created":"2024-07-11","cited_by_count":5,"area":null},{"id":"2504.20213","title":"Can Large Language Models Learn Formal Logic? A Data-Driven Training and Evaluation Framework","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2510.18184","title":"ActivationReasoning: Logical Reasoning in Latent Activation Spaces","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2404.04237","title":"GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language Models","created":"2024-04-05","cited_by_count":4,"area":"lr"},{"id":"2503.22693","title":"Bridging Language Models and Financial Analysis","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.19405","title":"CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems","created":"2025-05-26","cited_by_count":4,"area":"lr"},{"id":"2510.12722","title":"Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2601.00791","title":"Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning","created":"2026-01-02","cited_by_count":4,"area":"lr"},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","cited_by_count":4,"area":"mllm"},{"id":"2606.11893","title":"Beyond representational alignment with brain-guided language models for robust reasoning","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2502.09589","title":"Logical forms complement probability in understanding language model (and human) performance","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2505.10870","title":"Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate","created":"2025-05-16","cited_by_count":3,"area":"lr"},{"id":"2409.13728","title":"Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2410.12972","title":"KCIF: Knowledge-Conditioned Instruction Following","created":"2024-10-16","cited_by_count":2,"area":"lr"},{"id":"2508.17669","title":"A Taxonomy of Transcendence","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2509.15587","title":"DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models","created":"2025-09-19","cited_by_count":2,"area":"lr"},{"id":"2605.04920","title":"Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization","created":"2026-05-06","cited_by_count":2,"area":"deeprl"},{"id":"2605.11746","title":"When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2501.02825","title":"Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning","created":"2025-01-06","cited_by_count":1,"area":"lr"},{"id":"2504.07080","title":"DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning","created":"2025-04-09","cited_by_count":1,"area":"lr"},{"id":"2504.14089","title":"LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models","created":"2025-04-18","cited_by_count":1,"area":"lr"},{"id":"2505.04736","title":"The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2505.14313","title":"Teaching Small Language Models to Learn Logic through Meta-Learning","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2510.03873","title":"PoseGaze-AHP: A Knowledge-Based 3D Dataset for AI-Driven Ocular and Postural Diagnosis","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2604.25800","title":"Barriers to Universal Reasoning With Transformers (And How to Overcome Them)","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2502.17017","title":"Quantifying Logical Consistency in Transformers via Query-Key Alignment","created":"2025-02-24","cited_by_count":0,"area":"lr"},{"id":"2506.19089","title":"Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting","created":"2025-06-23","cited_by_count":0,"area":"wm"},{"id":"2512.10561","title":"Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2603.21736","title":"The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.23867","title":"Can VLMs Reason Robustly? A Neuro-Symbolic Investigation","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2606.19788","title":"CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.37203","title":"Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}