{"list":"other","total":73,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"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":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2409.04109","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","created":"2024-09-06","cited_by_count":363},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2404.07738","title":"ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models","created":"2024-04-11","cited_by_count":210},{"id":"2305.18189","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","created":"2023-05-29","cited_by_count":207},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199},{"id":"2309.05196","title":"Does Writing with Language Models Reduce Content Diversity?","created":"2023-09-11","cited_by_count":192},{"id":"2209.14958","title":"Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals","created":"2022-09-29","cited_by_count":191},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184},{"id":"2309.14556","title":"Art or Artifice? Large Language Models and the False Promise of Creativity","created":"2023-09-25","cited_by_count":172},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2409.13740","title":"Language agents achieve superhuman synthesis of scientific knowledge","created":"2024-09-10","cited_by_count":137},{"id":"2402.01536","title":"Homogenization Effects of Large Language Models on Human Creative Ideation","created":"2024-02-02","cited_by_count":127},{"id":"2312.03689","title":"Evaluating and Mitigating Discrimination in Language Model Decisions","created":"2023-12-06","cited_by_count":124},{"id":"2404.01268","title":"Mapping the Increasing Use of LLMs in Scientific Papers","created":"2024-04-01","cited_by_count":118},{"id":"2402.11436","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","created":"2024-02-18","cited_by_count":114},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92},{"id":"2407.13248","title":"Are Large Language Models Capable of Generating Human-Level Narratives?","created":"2024-07-18","cited_by_count":79},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77},{"id":"2311.08370","title":"SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models","created":"2023-11-14","cited_by_count":76},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72},{"id":"2210.13669","title":"Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing","created":"2022-10-25","cited_by_count":71},{"id":"2010.01717","title":"STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation","created":"2020-10-04","cited_by_count":56},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43},{"id":"2007.14435","title":"Towards Ecologically Valid Research on Language User Interfaces","created":"2020-07-28","cited_by_count":42},{"id":"2410.04265","title":"AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text","created":"2024-10-05","cited_by_count":42},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35},{"id":"2410.05613","title":"Stereotype or Personalization? User Identity Biases Chatbot Recommendations","created":"2024-10-08","cited_by_count":34},{"id":"2309.12570","title":"Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers","created":"2023-09-22","cited_by_count":32},{"id":"2309.13933","title":"Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey","created":"2023-09-25","cited_by_count":30},{"id":"2410.02653","title":"Measuring and Improving Persuasiveness of Large Language Models","created":"2024-10-03","cited_by_count":20},{"id":"2311.08469","title":"UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations","created":"2023-11-14","cited_by_count":19},{"id":"2406.18906","title":"Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets","created":"2024-06-27","cited_by_count":18},{"id":"2406.15267","title":"Evaluating Diversity in Automatic Poetry Generation","created":"2024-06-21","cited_by_count":17},{"id":"2308.13355","title":"WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AI","created":"2023-08-25","cited_by_count":13},{"id":"2401.09804","title":"Clickbait vs. Quality: How Engagement-Based Optimization Shapes the Content Landscape in Online Platforms","created":"2024-01-18","cited_by_count":13},{"id":"2406.14900","title":"Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation","created":"2024-06-21","cited_by_count":11},{"id":"2406.15885","title":"The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models","created":"2024-06-22","cited_by_count":10},{"id":"2406.17962","title":"Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework","created":"2024-06-25","cited_by_count":10},{"id":"2410.20739","title":"Gender Bias in LLM-generated Interview Responses","created":"2024-10-28","cited_by_count":10},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7},{"id":"2402.06221","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","created":"2024-02-09","cited_by_count":6},{"id":"2112.08414","title":"DSGPT: Domain-Specific Generative Pre-Training of Transformers for Text Generation in E-commerce Title and Review Summarization","created":"2021-12-15","cited_by_count":5},{"id":"2305.08152","title":"STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation","created":"2023-05-14","cited_by_count":5},{"id":"2405.13890","title":"Workshop Paper: An empirical study to understand how students use ChatGPT for writing essays and how it affects their ownership","created":"2024-05-22","cited_by_count":5},{"id":"2502.13221","title":"Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations","created":"2025-02-18","cited_by_count":2},{"id":"2103.05069","title":"Domain Controlled Title Generation with Human Evaluation","created":"2021-03-08","cited_by_count":1}],"next_cursor":null}