{"total":25,"rows":[{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2406.09279","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","created":"2024-06-13","cited_by_count":107,"area":"lr"},{"id":"2410.04707","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","created":"2024-10-07","cited_by_count":70,"area":"lr"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2503.18878","title":"I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2505.17407","title":"Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2503.00093","title":"Rethinking LLM Bias Probing Using Lessons from the Social Sciences","created":"2025-02-28","cited_by_count":7,"area":"lr"},{"id":"2605.20087","title":"ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions","created":"2026-05-19","cited_by_count":7,"area":"lr"},{"id":"2410.04407","title":"Lens: Rethinking Multilingual Enhancement for Large Language Models","created":"2024-10-06","cited_by_count":6,"area":"lr"},{"id":"2512.01222","title":"Unsupervised decoding of encoded reasoning using language model interpretability","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2502.05497","title":"DeepThink: Aligning Language Models with Domain-Specific User Intents","created":"2025-02-08","cited_by_count":2,"area":"lr"},{"id":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2510.03243","title":"Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2509.22750","title":"MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2606.24251","title":"Probing the Misaligned Thinking Process of Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2505.22767","title":"In Dialogue with Intelligence: Rethinking Large Language Models as Collective Knowledge","created":"2025-05-28","cited_by_count":0,"area":"lr"},{"id":"2605.01749","title":"Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2608.08451","title":"Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Chain Regularization","created":"2026-08-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}