{"list":"other","total":54,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"1906.05433","title":"Tackling Climate Change with Machine Learning","created":"2019-06-10","cited_by_count":265},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87},{"id":"2409.02897","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","created":"2024-09-04","cited_by_count":81},{"id":"2401.14656","title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","created":"2024-01-26","cited_by_count":80},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74},{"id":"2402.11451","title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","created":"2024-02-18","cited_by_count":70},{"id":"2405.08807","title":"SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation","created":"2024-05-14","cited_by_count":48},{"id":"2502.05151","title":"Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation","created":"2025-02-07","cited_by_count":42},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39},{"id":"2304.05510","title":"chatClimate: Grounding Conversational AI in Climate Science","created":"2023-04-11","cited_by_count":32},{"id":"2412.09569","title":"JuStRank: Benchmarking LLM Judges for System Ranking","created":"2024-12-12","cited_by_count":29},{"id":"2407.12856","title":"AI-AI Bias: large language models favor communications generated by large language models","created":"2024-07-09","cited_by_count":26},{"id":"2506.01241","title":"ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists","created":"2025-06-02","cited_by_count":24},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23},{"id":"2403.18381","title":"Improving Attributed Text Generation of Large Language Models via Preference Learning","created":"2024-03-27","cited_by_count":23},{"id":"2402.06204","title":"The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluate","created":"2024-02-09","cited_by_count":16},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16},{"id":"2501.08774","title":"How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering","created":"2025-01-15","cited_by_count":15},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15},{"id":"2406.10421","title":"SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading","created":"2024-06-14","cited_by_count":14},{"id":"2406.12319","title":"The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators","created":"2024-06-18","cited_by_count":11},{"id":"2506.06605","title":"MedCite: Can Language Models Generate Verifiable Text for Medicine?","created":"2025-06-07","cited_by_count":11},{"id":"2502.01159","title":"AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science","created":"2025-02-03","cited_by_count":9},{"id":"2505.06108","title":"LLMs Outperform Experts on Challenging Biology Benchmarks","created":"2025-05-09","cited_by_count":9},{"id":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5},{"id":"2409.14037","title":"Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators","created":"2024-09-21","cited_by_count":4},{"id":"2504.14856","title":"Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation","created":"2025-04-21","cited_by_count":4},{"id":"2507.07328","title":"Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery","created":"2025-07-09","cited_by_count":1}],"next_cursor":null}