{"total":100,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95,"area":null},{"id":"2104.01112","title":"NaturalProofs: Mathematical Theorem Proving in Natural Language","created":"2021-03-24","cited_by_count":81,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72,"area":null},{"id":"2410.03981","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","created":"2024-10-04","cited_by_count":66,"area":null},{"id":"2404.09939","title":"A Survey on Deep Learning for Theorem Proving","created":"2024-04-15","cited_by_count":57,"area":null},{"id":"2205.12443","title":"Generating Natural Language Proofs with Verifier-Guided Search","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49,"area":null},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2210.12217","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","created":"2022-10-21","cited_by_count":38,"area":null},{"id":"2201.06028","title":"Natural Language Deduction through Search over Statement Compositions","created":"2022-01-16","cited_by_count":35,"area":null},{"id":"2305.05976","title":"Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge","created":"2023-05-10","cited_by_count":32,"area":null},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2112.09054","title":"Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2310.09158","title":"Improving Large Language Models in Event Relation Logical Prediction","created":"2023-10-13","cited_by_count":17,"area":null},{"id":"2209.10492","title":"Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees","created":"2022-09-21","cited_by_count":14,"area":null},{"id":"2212.06295","title":"Despite \"super-human\" performance, current LLMs are unsuited for decisions about ethics and safety","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2306.04347","title":"World Models for Math Story Problems","created":"2023-06-07","cited_by_count":11,"area":null},{"id":"2410.01598","title":"Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendation","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2305.12710","title":"Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2410.23299","title":"FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware","created":"2024-10-15","cited_by_count":10,"area":null},{"id":"2111.12038","title":"Learning Symbolic Rules for Reasoning in Quasi-Natural Language","created":"2021-11-23","cited_by_count":9,"area":null},{"id":"2511.09008","title":"A Neurosymbolic Approach to Natural Language Formalization and Verification","created":"2025-11-12","cited_by_count":9,"area":null},{"id":"2109.08460","title":"Neural Unification for Logic Reasoning over Natural Language","created":"2021-09-17","cited_by_count":8,"area":null},{"id":"2112.08583","title":"Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2105.02486","title":"Towards General Natural Language Understanding with Probabilistic Worldbuilding","created":"2021-05-06","cited_by_count":7,"area":null},{"id":"2105.03417","title":"Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference","created":"2021-05-07","cited_by_count":7,"area":null},{"id":"2110.01509","title":"DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models","created":"2021-10-04","cited_by_count":7,"area":null},{"id":"2403.20322","title":"Towards a Framework for Evaluating Explanations in Automated Fact Verification","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2405.15722","title":"Models That Prove Their Own Correctness","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2608.19013","title":"Harness Continual Learning: Continual Adaptation Beyond Model Parameters","created":"2026-08-19","cited_by_count":6,"area":null},{"id":"2502.16757","title":"Entailment-Preserving First-order Logic Representations in Natural Language Entailment","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2506.09433","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2602.13237","title":"NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models","created":"2026-01-29","cited_by_count":5,"area":null},{"id":"2311.00694","title":"Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving","created":"2023-11-01","cited_by_count":4,"area":null},{"id":"2403.16097","title":"Can Language Models Pretend Solvers? Logic Code Simulation with LLMs","created":"2024-03-24","cited_by_count":4,"area":null},{"id":"2610.02076","title":"LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them","created":"2026-10-01","cited_by_count":4,"area":null},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2401.14043","title":"Towards Goal-oriented Prompt Engineering for Large Language Models: A Survey","created":"2024-01-25","cited_by_count":3,"area":null},{"id":"2403.06410","title":"A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2605.25230","title":"Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2605.30148","title":"Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.18557","title":"DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2509.23488","title":"Mapping Overlaps in Benchmarks through Perplexity in the Wild","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2602.04003","title":"When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2607.18921","title":"Circuit Claims Depend on What Is Extracted and How It Is Compared","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2607.27617","title":"Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2203.00162","title":"Do Transformers know symbolic rules, and would we know if they did?","created":"2022-02-19","cited_by_count":1,"area":null},{"id":"2212.11353","title":"Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2308.03581","title":"Towards Controllable Natural Language Inference through Lexical Inference Types","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2309.07624","title":"Dynamic MOdularized Reasoning for Compositional Structured Explanation Generation","created":"2023-09-14","cited_by_count":1,"area":null},{"id":"2405.04872","title":"Logical Negation Augmenting and Debiasing for Prompt-based Methods","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2502.19973","title":"Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios","created":"2025-02-27","cited_by_count":1,"area":null},{"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":"2508.15099","title":"Hydra: A Modular Architecture for Efficient Long-Context Reasoning","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2604.05396","title":"Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2608.10679","title":"ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2205.08954","title":"One-way Explainability Isn't The Message","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2208.14641","title":"Generating Intermediate Steps for NLI with Next-Step Supervision","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2311.08941","title":"Transformers in the Service of Description Logic-based Contexts","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2406.10660","title":"DIEKAE: Difference Injection for Efficient Knowledge Augmentation and Editing of Large Language Models","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2507.23167","title":"LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.14488","title":"Reasoning is about giving reasons","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.02476","title":"Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2511.11669","title":"H-Model: Dynamic Neural Architectures for Adaptive Processing","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2601.19605","title":"Decompose-and-Formalise: Recursively Verifiable Natural Language Inference","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.01132","title":"Don't Judge a Book by its Cover: Testing LLMs' Robustness Under Logical Obfuscation","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.18843","title":"ABD: Default Exception Abduction in Finite First Order Worlds","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2602.18956","title":"INDUCTION: Finite-Structure Concept Synthesis in First-Order Logic","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2604.06196","title":"Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.08305","title":"LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.11116","title":"The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.05097","title":"Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.10843","title":"Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.08435","title":"EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.27833","title":"From Reasoning Strings to Partial Orders: Verifier-Certified Rule Transport through Quotient Policy Optimization","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.32201","title":"Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36636","title":"What Makes Recurrence Effective in Looped Language Models?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38621","title":"When Scientific Contradictions Are Lost in Translation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39608","title":"Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05114","title":"Belief-Trajectory Energy: Measuring the Path to a Prediction","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.14021","title":"CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.14552","title":"LASER: Defeasible Certificate Search for Long-Range Protocol Dependencies","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18579","title":"Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19215","title":"Narrowing the Collaboration Gap, Probably","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19644","title":"Selective Reasoning for Typed Decision Models: When to Start, Read, and Stop","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}