{"list":"other","total":52,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"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":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2304.09542","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","created":"2023-04-19","cited_by_count":360},{"id":"2306.17563","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","created":"2023-06-30","cited_by_count":307},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176},{"id":"2204.07496","title":"Improving Passage Retrieval with Zero-Shot Question Generation","created":"2022-04-15","cited_by_count":165},{"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":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115},{"id":"2307.02762","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","created":"2023-07-06","cited_by_count":114},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112},{"id":"2403.07366","title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","created":"2024-03-12","cited_by_count":106},{"id":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105},{"id":"2404.13781","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","created":"2024-04-21","cited_by_count":90},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87},{"id":"2305.02156","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","created":"2023-05-03","cited_by_count":82},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74},{"id":"2402.13904","title":"Calibrating Large Language Models with Sample Consistency","created":"2024-02-21","cited_by_count":73},{"id":"2403.18349","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","created":"2024-03-27","cited_by_count":66},{"id":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50},{"id":"2405.18414","title":"Don't Forget to Connect! Improving RAG with Graph-based Reranking","created":"2024-05-28","cited_by_count":49},{"id":"2406.11678","title":"TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy","created":"2024-06-17","cited_by_count":47},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35},{"id":"2403.19216","title":"Are Large Language Models Good at Utility Judgments?","created":"2024-03-28","cited_by_count":22},{"id":"2402.14259","title":"Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond","created":"2024-02-22","cited_by_count":18},{"id":"2301.02998","title":"InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers","created":"2023-01-08","cited_by_count":14},{"id":"2410.06615","title":"QA-Calibration of Language Model Confidence Scores","created":"2024-10-09","cited_by_count":13},{"id":"2403.12499","title":"Listwise Generative Retrieval Models via a Sequential Learning Process","created":"2024-03-19","cited_by_count":11},{"id":"2411.04602","title":"Self-Calibrated Listwise Reranking with Large Language Models","created":"2024-11-07","cited_by_count":7},{"id":"2409.18409","title":"Generative Retrieval Meets Multi-Graded Relevance","created":"2024-09-27","cited_by_count":6},{"id":"2503.20430","title":"RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning","created":"2025-03-26","cited_by_count":6},{"id":"2405.01848","title":"RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank","created":"2024-05-03","cited_by_count":4},{"id":"2409.17460","title":"Towards More Relevant Product Search Ranking Via Large Language Models: An Empirical Study","created":"2024-09-26","cited_by_count":2},{"id":"2504.12063","title":"Optimizing Compound Retrieval Systems","created":"2025-04-16","cited_by_count":1}],"next_cursor":null}