{"total":112,"rows":[{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714,"area":null},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441,"area":null},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412,"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":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211,"area":null},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205,"area":"lr"},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"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,"area":null},{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171,"area":"lr"},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156,"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":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"area":"safety"},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2210.15230","title":"How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"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":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"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":"2305.12788","title":"GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs","created":"2023-05-22","cited_by_count":58,"area":null},{"id":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56,"area":null},{"id":"2305.09941","title":"\"I'm fully who I am\": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation","created":"2023-05-17","cited_by_count":56,"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":"2106.01465","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","created":"2021-06-02","cited_by_count":46,"area":null},{"id":"2101.10579","title":"Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs","created":"2021-01-26","cited_by_count":45,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2106.11783","title":"Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech","created":"2021-06-22","cited_by_count":42,"area":null},{"id":"2205.14219","title":"Controllable Text Generation with Neurally-Decomposed Oracle","created":"2022-05-27","cited_by_count":41,"area":null},{"id":"2102.04257","title":"Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities","created":"2021-02-03","cited_by_count":40,"area":null},{"id":"2203.08308","title":"Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction","created":"2022-03-15","cited_by_count":40,"area":null},{"id":"2203.12574","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","created":"2022-03-23","cited_by_count":40,"area":"distill"},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"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":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2104.05196","title":"StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer","created":"2021-04-12","cited_by_count":34,"area":null},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","cited_by_count":33,"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":"2109.06437","title":"Uncovering Implicit Gender Bias in Narratives through Commonsense Inference","created":"2021-09-14","cited_by_count":32,"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":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","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":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2202.05599","title":"ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization","created":"2022-02-11","cited_by_count":25,"area":null},{"id":"2305.15377","title":"Uncovering and Quantifying Social Biases in Code Generation","created":"2023-05-24","cited_by_count":25,"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":"2205.02392","title":"Robust Conversational Agents against Imperceptible Toxicity Triggers","created":"2022-05-05","cited_by_count":23,"area":"agents"},{"id":"2210.07269","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","created":"2022-10-13","cited_by_count":22,"area":"lr"},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2309.08836","title":"Bias and Fairness in Chatbots: An Overview","created":"2023-09-16","cited_by_count":20,"area":null},{"id":"2206.05395","title":"Why is constrained neural language generation particularly challenging?","created":"2022-06-11","cited_by_count":19,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2311.07884","title":"Fair Abstractive Summarization of Diverse Perspectives","created":"2023-11-14","cited_by_count":17,"area":null},{"id":"2108.01764","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","created":"2021-08-03","cited_by_count":16,"area":null},{"id":"2409.03659","title":"LLM-based multi-agent poetry generation in non-cooperative environments","created":"2024-09-05","cited_by_count":15,"area":"agents"},{"id":"2203.16165","title":"Symbolic music generation conditioned on continuous-valued emotions","created":"2022-03-30","cited_by_count":13,"area":null},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","cited_by_count":13,"area":null},{"id":"2306.15774","title":"Next Steps for Human-Centered Generative AI: A Technical Perspective","created":"2023-06-27","cited_by_count":13,"area":null},{"id":"2302.13136","title":"Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling","created":"2023-02-25","cited_by_count":12,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2405.18780","title":"Certifying Counterfactual Bias in LLMs","created":"2024-05-29","cited_by_count":10,"area":"safety"},{"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":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2203.13397","title":"GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2212.01810","title":"Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation","created":"2022-12-04","cited_by_count":8,"area":null},{"id":"2305.04978","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","created":"2023-05-08","cited_by_count":8,"area":"distill"},{"id":"2310.08795","title":"Mitigating Bias for Question Answering Models by Tracking Bias Influence","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2502.15419","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","created":"2025-02-21","cited_by_count":8,"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":"2212.01700","title":"Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts","created":"2022-12-03","cited_by_count":7,"area":null},{"id":"2408.03618","title":"A Logical Fallacy-Informed Framework for Argument Generation","created":"2024-08-07","cited_by_count":7,"area":"alignment"},{"id":"2410.03818","title":"Large Language Models can be Strong Self-Detoxifiers","created":"2024-10-04","cited_by_count":7,"area":"alignment"},{"id":"2209.12099","title":"Controllable Text Generation for Open-Domain Creativity and Fairness","created":"2022-09-24","cited_by_count":6,"area":null},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6,"area":"alignment"},{"id":"2406.11109","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2505.12349","title":"Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2109.06950","title":"Automatically Exposing Problems with Neural Dialog Models","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2209.06687","title":"How people talk about each other: Modeling Generalized Intergroup Bias and Emotion","created":"2022-09-14","cited_by_count":5,"area":null},{"id":"2212.08724","title":"DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2410.04628","title":"Control Large Language Models via Divide and Conquer","created":"2024-10-06","cited_by_count":5,"area":null},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2112.06953","title":"Controlled Cue Generation for Play Scripts","created":"2021-12-13","cited_by_count":4,"area":null},{"id":"2211.08451","title":"kogito: A Commonsense Knowledge Inference Toolkit","created":"2022-11-15","cited_by_count":4,"area":null},{"id":"2504.01819","title":"Implicit Bias Injection Attacks against Text-to-Image Diffusion Models","created":"2025-04-02","cited_by_count":4,"area":"diffusion"},{"id":"2601.17172","title":"Who Gets Which Message? Auditing Demographic Bias in LLM-Generated Targeted Text","created":"2026-01-23","cited_by_count":4,"area":null},{"id":"2305.16641","title":"Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children's Fairy Tales","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2310.11079","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models","created":"2023-10-17","cited_by_count":3,"area":"safety"},{"id":"2406.00548","title":"LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2305.16409","title":"Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2505.11958","title":"Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2508.09450","title":"From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2510.00232","title":"BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.17247","title":"From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models","created":"2025-10-20","cited_by_count":2,"area":"diffusion"},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2405.19299","title":"Expert-Guided Extinction of Toxic Tokens for Debiased Generation","created":"2024-05-29","cited_by_count":1,"area":null}],"next_cursor":"100"}