{"list":"other","total":69,"rows":[{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"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":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"1901.10002","title":"A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle","created":"2019-01-28","cited_by_count":193},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2302.04578","title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","created":"2023-02-09","cited_by_count":167},{"id":"2403.07183","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","created":"2024-03-11","cited_by_count":164},{"id":"2102.02503","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","created":"2021-02-04","cited_by_count":160},{"id":"2304.03738","title":"Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models","created":"2023-04-07","cited_by_count":148},{"id":"2404.12272","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","created":"2024-04-18","cited_by_count":144},{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128},{"id":"2403.04957","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","created":"2024-03-07","cited_by_count":119},{"id":"2206.05229","title":"Measuring the Carbon Intensity of AI in Cloud Instances","created":"2022-06-10","cited_by_count":111},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104},{"id":"1602.03506","title":"Research Priorities for Robust and Beneficial Artificial Intelligence","created":"2016-02-10","cited_by_count":74},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71},{"id":"2403.07918","title":"On the Societal Impact of Open Foundation Models","created":"2024-02-27","cited_by_count":65},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62},{"id":"2306.06130","title":"Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet","created":"2023-06-08","cited_by_count":54},{"id":"2304.03271","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","created":"2023-04-06","cited_by_count":44},{"id":"2303.09387","title":"Characterizing Manipulation from AI Systems","created":"2023-03-16","cited_by_count":43},{"id":"2101.06060","title":"The Challenge of Value Alignment: from Fairer Algorithms to AI Safety","created":"2021-01-15","cited_by_count":35},{"id":"2401.05749","title":"A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism","created":"2024-01-11","cited_by_count":35},{"id":"2404.15058","title":"A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI","created":"2024-04-23","cited_by_count":34},{"id":"2303.08721","title":"Artificial Influence: An Analysis Of AI-Driven Persuasion","created":"2023-03-15","cited_by_count":33},{"id":"2012.09995","title":"Data Leverage: A Framework for Empowering the Public in its Relationship with Technology Companies","created":"2020-12-18","cited_by_count":26},{"id":"2307.07367","title":"Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow","created":"2023-07-14","cited_by_count":22},{"id":"2210.02667","title":"A Human Rights-Based Approach to Responsible AI","created":"2022-10-06","cited_by_count":20},{"id":"1912.07376","title":"Algorithmic Injustices: Towards a Relational Ethics","created":"2019-12-16","cited_by_count":11},{"id":"2302.10856","title":"Overview of the TREC 2021 Fair Ranking Track","created":"2023-02-21","cited_by_count":7},{"id":"2403.03344","title":"Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation","created":"2024-03-05","cited_by_count":7},{"id":"2305.13238","title":"The Dimensions of Data Labor: A Road Map for Researchers, Activists, and Policymakers to Empower Data Producers","created":"2023-05-22","cited_by_count":6},{"id":"2306.16668","title":"Beyond CO2 Emissions: The Overlooked Impact of Water Consumption of Information Retrieval Models","created":"2023-06-29","cited_by_count":6},{"id":"2310.01297","title":"Co-audit: tools to help humans double-check AI-generated content","created":"2023-10-02","cited_by_count":5},{"id":"2403.17901","title":"Search and Society: Reimagining Information Access for Radical Futures","created":"2024-03-26","cited_by_count":4},{"id":"1912.00757","title":"Mapping the Potential and Pitfalls of \"Data Dividends\" as a Means of Sharing the Profits of Artificial Intelligence","created":"2019-11-19","cited_by_count":1},{"id":"2209.04011","title":"RecSys Fairness Metrics: Many to Use But Which One To Choose?","created":"2022-09-08","cited_by_count":1},{"id":"2306.12807","title":"AI could create a perfect storm of climate misinformation","created":"2023-06-22","cited_by_count":1},{"id":"2312.10076","title":"A Framework for Exploring the Consequences of AI-Mediated Enterprise Knowledge Access and Identifying Risks to Workers","created":"2023-12-08","cited_by_count":1}],"next_cursor":null}