{"total":57,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"area":"lr"},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"id":"2408.00724","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","created":"2024-08-01","cited_by_count":290,"area":"lr"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2310.06786","title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text","created":"2023-10-10","cited_by_count":155,"area":"lr"},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89,"area":"lr"},{"id":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"area":"lr"},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51,"area":"lr"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2504.19483","title":"Improving Reasoning Performance in Large Language Models via Representation Engineering","created":"2025-04-28","cited_by_count":23,"area":"lr"},{"id":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19,"area":"lr"},{"id":"2501.06254","title":"Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words","created":"2025-01-09","cited_by_count":18,"area":"lr"},{"id":"2404.03134","title":"Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?","created":"2024-04-04","cited_by_count":17,"area":"lr"},{"id":"2406.13803","title":"LLMs as Models for Analogical Reasoning","created":"2024-06-19","cited_by_count":16,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2402.11900","title":"Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models","created":"2024-02-19","cited_by_count":14,"area":"lr"},{"id":"2405.20834","title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning","created":"2024-05-31","cited_by_count":14,"area":"lr"},{"id":"2306.07536","title":"TART: A plug-and-play Transformer module for task-agnostic reasoning","created":"2023-06-13","cited_by_count":10,"area":"lr"},{"id":"2402.12091","title":"Do Large Language Models Understand Logic or Just Mimick Context?","created":"2024-02-19","cited_by_count":10,"area":"lr"},{"id":"2411.02528","title":"What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length","created":"2024-11-04","cited_by_count":10,"area":"lr"},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2604.06374","title":"The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models","created":"2026-04-07","cited_by_count":7,"area":"lr"},{"id":"2402.14404","title":"On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe","created":"2024-02-22","cited_by_count":6,"area":"lr"},{"id":"2410.06524","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","created":"2024-10-09","cited_by_count":6,"area":"lr"},{"id":"2305.02897","title":"An automatically discovered chain-of-thought prompt generalizes to novel models and datasets","created":"2023-05-04","cited_by_count":5,"area":"lr"},{"id":"2501.00712","title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","created":"2025-01-01","cited_by_count":4,"area":"lr"},{"id":"2512.24503","title":"Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice","created":"2025-12-30","cited_by_count":3,"area":"lr"},{"id":"2405.10251","title":"A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks","created":"2024-05-16","cited_by_count":2,"area":"lr"},{"id":"2503.23779","title":"WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization","created":"2025-03-31","cited_by_count":2,"area":"lr"},{"id":"2505.23247","title":"Accelerating RLHF Training with Reward Variance Increase","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2602.12143","title":"STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2602.20528","title":"Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning","created":"2026-02-24","cited_by_count":2,"area":"lr"},{"id":"2406.12620","title":"What Makes Two Language Models Think Alike?","created":"2024-06-18","cited_by_count":1,"area":"lr"},{"id":"2507.14777","title":"Rethinking Memorization Measures and their Implications in Large Language Models","created":"2025-07-20","cited_by_count":1,"area":"lr"},{"id":"2508.06974","title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"lr"},{"id":"2512.20812","title":"Semantic Deception: When Reasoning Models Can't Compute an Addition","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2604.00430","title":"Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2605.28919","title":"CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.16517","title":"How Post-Training Shapes Biological Reasoning Models","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2608.15507","title":"Do Language Models Consistently Encode the Current Year?","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2503.01464","title":"Rethinking Data: Towards Better Performing Domain-Specific Small Language Models","created":"2025-03-03","cited_by_count":0,"area":"lr"},{"id":"2503.20103","title":"Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought Disorder","created":"2025-03-25","cited_by_count":0,"area":"lr"},{"id":"2505.14852","title":"EasyMath: A 0-shot Math Benchmark for SLMs","created":"2025-05-20","cited_by_count":0,"area":"lr"},{"id":"2510.05133","title":"Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2606.05932","title":"A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR","created":"2026-06-04","cited_by_count":0,"area":"lr"},{"id":"2606.10740","title":"When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.26470","title":"CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.31068","title":"Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.25643","title":"Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.29845","title":"Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.36535","title":"When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.14500","title":"Rethinking Activation Functions: Reducing Bias Can Improve Learning","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}