{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"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":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2005.10608","title":"Unsupervised Quality Estimation for Neural Machine Translation","created":"2020-05-21","cited_by_count":211},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150},{"id":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","cited_by_count":131},{"id":"2308.16175","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","created":"2023-08-30","cited_by_count":122},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117},{"id":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105},{"id":"2510.01171","title":"Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity","created":"2025-10-01","cited_by_count":105},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92},{"id":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83},{"id":"1910.11385","title":"Calibration tests in multi-class classification: A unifying framework","created":"2019-10-24","cited_by_count":79},{"id":"2503.00031","title":"Efficient Test-Time Scaling via Self-Calibration","created":"2025-02-25","cited_by_count":75},{"id":"2402.13904","title":"Calibrating Large Language Models with Sample Consistency","created":"2024-02-21","cited_by_count":73},{"id":"1912.09024","title":"Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanations","created":"2019-12-19","cited_by_count":64},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62},{"id":"2409.19817","title":"Calibrating Language Models with Adaptive Temperature Scaling","created":"2024-09-29","cited_by_count":58},{"id":"2508.18847","title":"ConfTuner: Training Large Language Models to Express Their Confidence Verbally","created":"2025-08-26","cited_by_count":39},{"id":"2511.02734","title":"CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents","created":"2025-11-04","cited_by_count":33},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32},{"id":"2509.21766","title":"UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios","created":"2025-09-26","cited_by_count":26},{"id":"2506.07671","title":"GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation","created":"2025-06-09","cited_by_count":18},{"id":"2505.24778","title":"Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?","created":"2025-05-30","cited_by_count":16},{"id":"2412.11854","title":"Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference","created":"2024-12-16","cited_by_count":15},{"id":"2510.02044","title":"Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage","created":"2025-10-02","cited_by_count":15},{"id":"2505.07459","title":"Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis","created":"2025-05-12","cited_by_count":14},{"id":"2412.20251","title":"ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty","created":"2024-12-28","cited_by_count":10},{"id":"2201.05793","title":"A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases","created":"2022-01-15","cited_by_count":9},{"id":"2412.20309","title":"Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain","created":"2024-12-29","cited_by_count":9},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9},{"id":"2506.03100","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","created":"2025-06-03","cited_by_count":4}],"next_cursor":null}