{"total":299,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027,"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":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609,"area":null},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327,"area":null},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277,"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":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199,"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":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"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":"2402.06925","title":"A Thorough Examination of Decoding Methods in the Era of LLMs","created":"2024-02-10","cited_by_count":114,"area":null},{"id":"2402.03375","title":"BetterV: Controlled Verilog Generation with Discriminative Guidance","created":"2024-02-03","cited_by_count":100,"area":null},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2401.08565","title":"Tuning Language Models by Proxy","created":"2024-01-16","cited_by_count":89,"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":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2108.01850","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","created":"2021-08-04","cited_by_count":70,"area":null},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70,"area":null},{"id":"2202.04173","title":"Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models","created":"2022-02-08","cited_by_count":68,"area":null},{"id":"2205.00049","title":"Prompt Consistency for Zero-Shot Task Generalization","created":"2022-04-29","cited_by_count":67,"area":null},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67,"area":null},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2205.12558","title":"Gradient-Based Constrained Sampling from Language Models","created":"2022-05-25","cited_by_count":64,"area":null},{"id":"2210.08750","title":"Keep Me Updated! Memory Management in Long-term Conversations","created":"2022-10-17","cited_by_count":63,"area":null},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","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":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2410.16491","title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","created":"2024-10-21","cited_by_count":50,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2405.02750","title":"Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding","created":"2024-05-04","cited_by_count":49,"area":null},{"id":"2305.13632","title":"Detecting and Mitigating Hallucinations in Multilingual Summarisation","created":"2023-05-23","cited_by_count":48,"area":null},{"id":"2308.07968","title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","created":"2023-08-15","cited_by_count":48,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2310.09044","title":"KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","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":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41,"area":null},{"id":"2109.00087","title":"It's not Rocket Science : Interpreting Figurative Language in Narratives","created":"2021-08-31","cited_by_count":39,"area":null},{"id":"2212.08635","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","created":"2022-12-16","cited_by_count":39,"area":null},{"id":"2403.03640","title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","created":"2024-03-06","cited_by_count":38,"area":null},{"id":"2409.07394","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","created":"2024-09-11","cited_by_count":37,"area":null},{"id":"2211.03044","title":"Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning","created":"2022-11-06","cited_by_count":36,"area":null},{"id":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2210.02889","title":"A Distributional Lens for Multi-Aspect Controllable Text Generation","created":"2022-10-06","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":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2402.11889","title":"ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding","created":"2024-02-19","cited_by_count":32,"area":null},{"id":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2210.09551","title":"DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation","created":"2022-10-18","cited_by_count":30,"area":null},{"id":"2204.00862","title":"CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation","created":"2022-04-02","cited_by_count":29,"area":null},{"id":"2205.04304","title":"CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech","created":"2022-05-09","cited_by_count":29,"area":null},{"id":"2303.17574","title":"Elastic Weight Removal for Faithful and Abstractive Dialogue Generation","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2305.01628","title":"The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers","created":"2023-05-02","cited_by_count":29,"area":null},{"id":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2212.08307","title":"Controllable Text Generation via Probability Density Estimation in the Latent Space","created":"2022-12-16","cited_by_count":27,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2401.00690","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","created":"2024-01-01","cited_by_count":27,"area":null},{"id":"2311.00233","title":"Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions","created":"2023-11-01","cited_by_count":24,"area":null},{"id":"2210.12365","title":"NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2410.09300","title":"Nudging: Inference-time Alignment of LLMs via Guided Decoding","created":"2024-10-11","cited_by_count":23,"area":null},{"id":"2406.08824","title":"LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions","created":"2024-06-13","cited_by_count":22,"area":null},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2405.15454","title":"LiSeCo: Linear Semantic Control for Language Generation","created":"2024-05-24","cited_by_count":20,"area":null},{"id":"2409.03363","title":"Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding","created":"2024-09-05","cited_by_count":20,"area":null},{"id":"2203.03072","title":"Leashing the Inner Demons: Self-Detoxification for Language Models","created":"2022-03-06","cited_by_count":19,"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":"2408.12325","title":"Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2110.07520","title":"Comparative Opinion Summarization via Collaborative Decoding","created":"2021-10-14","cited_by_count":18,"area":null},{"id":"2212.10466","title":"Controllable Text Generation with Language Constraints","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2401.06947","title":"Parameter-Efficient Detoxification with Contrastive Decoding","created":"2024-01-13","cited_by_count":18,"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":"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":"2408.15666","title":"StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements","created":"2024-08-28","cited_by_count":18,"area":null},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2306.00784","title":"Interpretable Math Word Problem Solution Generation Via Step-by-step Planning","created":"2023-06-01","cited_by_count":17,"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":"2302.07388","title":"Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models","created":"2023-02-14","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":"2402.11218","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","created":"2024-02-17","cited_by_count":16,"area":null},{"id":"2403.11558","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","created":"2024-03-18","cited_by_count":16,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","cited_by_count":16,"area":null},{"id":"2305.14341","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2311.07167","title":"STEER: Unified Style Transfer with Expert Reinforcement","created":"2023-11-13","cited_by_count":14,"area":null}],"next_cursor":"100"}