{"list":"other","total":59,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"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":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95},{"id":"2405.12205","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","created":"2024-05-20","cited_by_count":84},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80},{"id":"2308.05342","title":"Metacognitive Prompting Improves Understanding in Large Language Models","created":"2023-08-10","cited_by_count":58},{"id":"2410.07176","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56},{"id":"2010.12527","title":"Answering Open-Domain Questions of Varying Reasoning Steps from Text","created":"2020-10-23","cited_by_count":43},{"id":"2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","created":"2025-05-19","cited_by_count":41},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40},{"id":"2410.13509","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","created":"2024-10-17","cited_by_count":33},{"id":"2502.19918","title":"Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":33},{"id":"2502.12961","title":"Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger","created":"2025-02-18","cited_by_count":30},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23},{"id":"2412.15176","title":"Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure","created":"2024-12-19","cited_by_count":18},{"id":"2501.03681","title":"SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment","created":"2025-01-07","cited_by_count":18},{"id":"2309.16459","title":"Augmenting LLMs with Knowledge: A survey on hallucination prevention","created":"2023-09-28","cited_by_count":16},{"id":"2410.06615","title":"QA-Calibration of Language Model Confidence Scores","created":"2024-10-09","cited_by_count":13},{"id":"2503.02233","title":"Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling","created":"2025-03-04","cited_by_count":13},{"id":"2502.15543","title":"ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation","created":"2025-02-21","cited_by_count":11},{"id":"2505.20903","title":"Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?","created":"2025-05-27","cited_by_count":11},{"id":"2505.12716","title":"Shadow-FT: Tuning Instruct Model via Training on Paired Base Model","created":"2025-05-19","cited_by_count":10},{"id":"2506.08410","title":"Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens","created":"2025-06-10","cited_by_count":10},{"id":"2410.08821","title":"DeepNote: Note-Centric Deep Retrieval-Augmented Generation","created":"2024-10-11","cited_by_count":8},{"id":"2411.08028","title":"Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data","created":"2024-11-12","cited_by_count":8},{"id":"2505.13529","title":"BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs","created":"2025-05-18","cited_by_count":8},{"id":"2601.03822","title":"ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition","created":"2026-01-07","cited_by_count":8},{"id":"2408.09017","title":"Meta Knowledge for Retrieval Augmented Large Language Models","created":"2024-08-16","cited_by_count":6},{"id":"2504.08761","title":"UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation","created":"2025-03-31","cited_by_count":6},{"id":"2510.13501","title":"Confidence as a Reward: Transforming LLMs into Reward Models","created":"2025-10-15","cited_by_count":5},{"id":"2505.22318","title":"Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds","created":"2025-05-28","cited_by_count":3},{"id":"2508.18381","title":"Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models","created":"2025-08-25","cited_by_count":3},{"id":"2508.09460","title":"Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation","created":"2025-08-13","cited_by_count":2},{"id":"2505.24388","title":"ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation","created":"2025-05-30","cited_by_count":1}],"next_cursor":null}