{"list":"other","total":53,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"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":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129},{"id":"2311.04897","title":"Future Lens: Anticipating Subsequent Tokens from a Single Hidden State","created":"2023-11-08","cited_by_count":121},{"id":"1808.10006","title":"Correcting Length Bias in Neural Machine Translation","created":"2018-08-29","cited_by_count":120},{"id":"2404.10198","title":"ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence","created":"2024-04-16","cited_by_count":113},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101},{"id":"2311.01740","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","created":"2023-11-03","cited_by_count":90},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67},{"id":"2309.12236","title":"Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing","created":"2023-09-21","cited_by_count":63},{"id":"2010.09697","title":"Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent","created":"2020-10-19","cited_by_count":40},{"id":"2501.08292","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","created":"2025-01-14","cited_by_count":34},{"id":"2402.12865","title":"Backward Lens: Projecting Language Model Gradients into the Vocabulary Space","created":"2024-02-20","cited_by_count":32},{"id":"2503.10996","title":"Taming Knowledge Conflicts in Language Models","created":"2025-03-14","cited_by_count":30},{"id":"2403.09037","title":"The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?","created":"2024-03-14","cited_by_count":26},{"id":"2406.12824","title":"From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries","created":"2024-06-18","cited_by_count":16},{"id":"2504.20168","title":"MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools","created":"2025-04-28","cited_by_count":15},{"id":"2008.09049","title":"Discovering Useful Sentence Representations from Large Pretrained Language Models","created":"2020-08-20","cited_by_count":6},{"id":"2506.02132","title":"Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models","created":"2025-06-02","cited_by_count":5}],"next_cursor":null}