{"total":377,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832,"area":null},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672,"area":"safety"},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"area":"alignment"},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513,"area":"diffusion"},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337,"area":null},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"area":null},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2201.06796","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","created":"2022-01-18","cited_by_count":249,"area":null},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187,"area":null},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181,"area":null},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"area":null},{"id":"2303.10130","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","created":"2023-03-17","cited_by_count":176,"area":null},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2307.00184","title":"Personality Traits in Large Language Models","created":"2023-07-01","cited_by_count":169,"area":null},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168,"area":null},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143,"area":"alignment"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135,"area":"safety"},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124,"area":"lr"},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123,"area":"diffusion"},{"id":"2404.07103","title":"Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs","created":"2024-04-10","cited_by_count":119,"area":"lr"},{"id":"2306.10070","title":"Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health","created":"2023-06-15","cited_by_count":118,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2310.15819","title":"Generative Language Models Exhibit Social Identity Biases","created":"2023-10-24","cited_by_count":111,"area":null},{"id":"2403.00811","title":"Cognitive Bias in Decision-Making with LLMs","created":"2024-02-25","cited_by_count":106,"area":null},{"id":"2203.07785","title":"The Ghost in the Machine has an American accent: value conflict in GPT-3","created":"2022-03-15","cited_by_count":105,"area":null},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98,"area":"safety"},{"id":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2402.02680","title":"Large Language Models are Geographically Biased","created":"2024-02-05","cited_by_count":93,"area":"wm"},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"area":null},{"id":"2310.15337","title":"Moral Foundations of Large Language Models","created":"2023-10-23","cited_by_count":85,"area":null},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76,"area":null},{"id":"2403.14117","title":"A Design Space for Intelligent and Interactive Writing Assistants","created":"2024-03-21","cited_by_count":76,"area":null},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74,"area":null},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68,"area":null},{"id":"2402.09091","title":"Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues","created":"2024-02-14","cited_by_count":68,"area":"safety"},{"id":"2307.14385","title":"Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data","created":"2023-07-26","cited_by_count":66,"area":null},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62,"area":"alignment"},{"id":"2308.09067","title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2409.11360","title":"AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances","created":"2024-09-17","cited_by_count":60,"area":null},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2304.02020","title":"A Bibliometric Review of Large Language Models Research from 2017 to 2023","created":"2023-04-03","cited_by_count":57,"area":null},{"id":"2310.15007","title":"Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models","created":"2023-10-23","cited_by_count":56,"area":"safety"},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"area":null},{"id":"2310.11877","title":"The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models","created":"2023-10-18","cited_by_count":55,"area":null},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2201.10474","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","created":"2022-01-25","cited_by_count":53,"area":null},{"id":"2303.09136","title":"A Short Survey of Viewing Large Language Models in Legal Aspect","created":"2023-03-16","cited_by_count":52,"area":null},{"id":"2211.01528","title":"Fair and Optimal Classification via Post-Processing","created":"2022-11-03","cited_by_count":51,"area":null},{"id":"2306.01857","title":"Knowledge of cultural moral norms in large language models","created":"2023-06-02","cited_by_count":51,"area":null},{"id":"2306.05550","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","created":"2023-06-08","cited_by_count":51,"area":null},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51,"area":null},{"id":"2402.04105","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","created":"2024-02-06","cited_by_count":51,"area":null},{"id":"2302.02463","title":"Nationality Bias in Text Generation","created":"2023-02-05","cited_by_count":50,"area":null},{"id":"2406.04428","title":"MoralBench: Moral Evaluation of LLMs","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2305.12268","title":"Patton: Language Model Pretraining on Text-Rich Networks","created":"2023-05-20","cited_by_count":49,"area":null},{"id":"2402.18050","title":"MEGAnno+: A Human-LLM Collaborative Annotation System","created":"2024-02-28","cited_by_count":47,"area":null},{"id":"2306.11932","title":"Opportunities and Risks of LLMs for Scalable Deliberation with Polis","created":"2023-06-20","cited_by_count":42,"area":null},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2308.02053","title":"The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations","created":"2023-08-03","cited_by_count":41,"area":null},{"id":"2403.08251","title":"Emergence of Social Norms in Generative Agent Societies: Principles and Architecture","created":"2024-03-13","cited_by_count":41,"area":"agents"},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"area":null},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2305.10510","title":"ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages","created":"2023-05-17","cited_by_count":34,"area":null},{"id":"2502.13175","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","created":"2025-02-18","cited_by_count":34,"area":null},{"id":"2503.12356","title":"Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation","created":"2025-03-16","cited_by_count":33,"area":"diffusion"},{"id":"2111.05204","title":"Reason first, then respond: Modular Generation for Knowledge-infused Dialogue","created":"2021-11-09","cited_by_count":32,"area":null},{"id":"2303.15772","title":"Ecosystem Graphs: The Social Footprint of Foundation Models","created":"2023-03-28","cited_by_count":32,"area":null}],"next_cursor":"100"}