{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297},{"id":"2302.10205","title":"ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT","created":"2023-02-20","cited_by_count":250},{"id":"2402.14762","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","created":"2024-02-22","cited_by_count":250},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236},{"id":"1906.10742","title":"Machine Learning Testing: Survey, Landscapes and Horizons","created":"2019-06-19","cited_by_count":218},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"2004.04494","title":"MuTual: A Dataset for Multi-Turn Dialogue Reasoning","created":"2020-04-09","cited_by_count":115},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105},{"id":"2009.13570","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","created":"2020-09-28","cited_by_count":89},{"id":"2401.16745","title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","created":"2024-01-30","cited_by_count":81},{"id":"2002.12543","title":"Metamorphic Testing: A New Approach for Generating Next Test Cases","created":"2020-02-28","cited_by_count":75},{"id":"2404.03868","title":"Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction","created":"2024-04-05","cited_by_count":70},{"id":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37},{"id":"2310.13650","title":"BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues","created":"2023-10-20","cited_by_count":34},{"id":"1805.11824","title":"Anaphora and Coreference Resolution: A Review","created":"2018-05-30","cited_by_count":31},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31},{"id":"2302.05706","title":"MTTM: Metamorphic Testing for Textual Content Moderation Software","created":"2023-02-11","cited_by_count":22},{"id":"2410.15576","title":"A Survey of Conversational Search","created":"2024-10-21","cited_by_count":22},{"id":"2311.09820","title":"IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance","created":"2023-11-16","cited_by_count":20},{"id":"2312.06056","title":"METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualities","created":"2023-12-11","cited_by_count":20},{"id":"2310.07301","title":"Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models","created":"2023-10-11","cited_by_count":16},{"id":"2405.00648","title":"Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models","created":"2024-05-01","cited_by_count":14},{"id":"1911.10776","title":"Filling Conversation Ellipsis for Better Social Dialog Understanding","created":"2019-11-25","cited_by_count":7},{"id":"2309.03554","title":"Software Testing of Generative AI Systems: Challenges and Opportunities","created":"2023-09-07","cited_by_count":7},{"id":"2410.04834","title":"As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss","created":"2024-10-07","cited_by_count":6},{"id":"2209.04595","title":"OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue","created":"2022-09-10","cited_by_count":4},{"id":"2403.05814","title":"MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs","created":"2024-03-09","cited_by_count":4}],"next_cursor":null}