{"total":148,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860,"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":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"area":null},{"id":"2302.00070","title":"Debiasing Vision-Language Models via Biased Prompts","created":"2023-01-31","cited_by_count":149,"area":"mllm"},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148,"area":null},{"id":"2302.00560","title":"Co-Writing with Opinionated Language Models Affects Users' Views","created":"2023-02-01","cited_by_count":148,"area":null},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129,"area":null},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112,"area":null},{"id":"2403.00811","title":"Cognitive Bias in Decision-Making with LLMs","created":"2024-02-25","cited_by_count":106,"area":null},{"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":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","cited_by_count":83,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77,"area":null},{"id":"2203.13928","title":"On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations","created":"2022-03-25","cited_by_count":75,"area":null},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73,"area":null},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65,"area":"mllm"},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"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":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"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":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"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":"2402.11190","title":"Disclosure and Mitigation of Gender Bias in LLMs","created":"2024-02-17","cited_by_count":49,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2212.10276","title":"Identifying and Manipulating the Personality Traits of Language Models","created":"2022-12-20","cited_by_count":40,"area":null},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"area":null},{"id":"2309.09825","title":"Bias of AI-Generated Content: An Examination of News Produced by Large Language Models","created":"2023-09-18","cited_by_count":38,"area":null},{"id":"2310.05280","title":"Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems","created":"2023-10-08","cited_by_count":37,"area":null},{"id":"2406.03712","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","created":"2024-06-06","cited_by_count":34,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2311.00306","title":"Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27,"area":"mllm"},{"id":"2107.07691","title":"Intersectional Bias in Causal Language Models","created":"2021-07-16","cited_by_count":24,"area":null},{"id":"2109.11708","title":"Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding","created":"2021-09-24","cited_by_count":23,"area":null},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2211.02069","title":"LMentry: A Language Model Benchmark of Elementary Language Tasks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2306.15298","title":"Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2407.10241","title":"BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs","created":"2024-07-14","cited_by_count":21,"area":null},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2106.08680","title":"Evaluating Gender Bias in Hindi-English Machine Translation","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2405.00705","title":"SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning","created":"2024-04-23","cited_by_count":19,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2501.14844","title":"Unmasking Conversational Bias in AI Multiagent Systems","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2112.07605","title":"The King is Naked: on the Notion of Robustness for Natural Language Processing","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2302.14003","title":"Systematic Rectification of Language Models via Dead-end Analysis","created":"2023-02-27","cited_by_count":16,"area":null},{"id":"2306.06135","title":"Safety and Fairness for Content Moderation in Generative Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2208.03843","title":"Counterfactual Fairness Is Basically Demographic Parity","created":"2022-08-07","cited_by_count":15,"area":null},{"id":"2310.14777","title":"Geographical Erasure in Language Generation","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2303.10131","title":"She Elicits Requirements and He Tests: Software Engineering Gender Bias in Large Language Models","created":"2023-03-17","cited_by_count":12,"area":null},{"id":"2310.12318","title":"The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis","created":"2023-10-18","cited_by_count":12,"area":null},{"id":"2109.02403","title":"Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction","created":"2021-09-06","cited_by_count":11,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2402.13462","title":"Potential and Challenges of Model Editing for Social Debiasing","created":"2024-02-21","cited_by_count":10,"area":null},{"id":"2405.13025","title":"A survey on fairness of large language models in e-commerce: progress, application, and challenge","created":"2024-05-15","cited_by_count":10,"area":null},{"id":"2104.05232","title":"Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation","created":"2021-04-12","cited_by_count":9,"area":null},{"id":"2302.13382","title":"Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communication","created":"2023-02-26","cited_by_count":9,"area":null},{"id":"2305.11348","title":"In the Name of Fairness: Assessing the Bias in Clinical Record De-identification","created":"2023-05-18","cited_by_count":9,"area":null},{"id":"2305.12757","title":"This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2407.10853","title":"Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2204.10365","title":"Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2211.02882","title":"HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models","created":"2022-11-05","cited_by_count":8,"area":null},{"id":"2305.11673","title":"Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2402.10353","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2210.03826","title":"An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation","created":"2022-10-07","cited_by_count":7,"area":null},{"id":"2408.00992","title":"Fairness in Large Language Models in Three Hours","created":"2024-08-02","cited_by_count":7,"area":null},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2210.15500","title":"COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2501.00418","title":"Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2503.00024","title":"Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2505.15524","title":"Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs","created":"2025-05-21","cited_by_count":6,"area":"mechinterp"},{"id":"2205.00320","title":"Detoxifying Language Models with a Toxic Corpus","created":"2022-04-30","cited_by_count":5,"area":null},{"id":"2207.02272","title":"Pretraining on Interactions for Learning Grounded Affordance Representations","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2303.06223","title":"Who's Thinking? A Push for Human-Centered Evaluation of LLMs using the XAI Playbook","created":"2023-03-10","cited_by_count":5,"area":"lr"},{"id":"2306.07152","title":"Measuring Sentiment Bias in Machine Translation","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2411.19240","title":"How far can bias go? Tracing bias from pretraining data to alignment","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2501.03112","title":"LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases","created":"2025-01-06","cited_by_count":5,"area":null},{"id":"2502.11425","title":"Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models","created":"2025-02-17","cited_by_count":5,"area":"lr"},{"id":"2204.07289","title":"Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Prompts","created":"2022-04-15","cited_by_count":4,"area":null}],"next_cursor":"100"}