{"list":"other","total":53,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2502.02737","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","created":"2025-02-04","cited_by_count":335},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"2604.00626","title":"A Survey of On-Policy Distillation for Large Language Models","created":"2026-04-01","cited_by_count":163},{"id":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86},{"id":"2512.16649","title":"JustRL: Scaling a 1.5B LLM with a Simple RL Recipe","created":"2025-12-18","cited_by_count":64},{"id":"2607.02234","title":"Purified OPSD: On-Policy Self-Distillation Without Losing How to Think","created":"2026-07-02","cited_by_count":31},{"id":"2508.13743","title":"Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA","created":"2025-08-19","cited_by_count":18},{"id":"2606.27377","title":"DanceOPD: On-Policy Generative Field Distillation","created":"2026-06-25","cited_by_count":14},{"id":"2505.24164","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","created":"2025-05-30","cited_by_count":13},{"id":"2409.10955","title":"Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style","created":"2024-09-17","cited_by_count":11},{"id":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3}],"next_cursor":null}