{"total":503,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896,"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":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470,"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":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396,"area":"alignment"},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270,"area":"distill"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225,"area":null},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"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":"2210.17432","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","created":"2022-10-31","cited_by_count":194,"area":"diffusion"},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185,"area":"alignment"},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154,"area":null},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"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":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"area":null},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124,"area":"lr"},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122,"area":"alignment"},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120,"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":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113,"area":"safety"},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111,"area":null},{"id":"2204.01171","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","created":"2022-04-03","cited_by_count":108,"area":null},{"id":"2312.16682","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","created":"2023-12-27","cited_by_count":108,"area":"alignment"},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100,"area":"offlinerl"},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94,"area":null},{"id":"2305.06849","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","created":"2023-05-11","cited_by_count":93,"area":null},{"id":"2109.09115","title":"Do Long-Range Language Models Actually Use Long-Range Context?","created":"2021-09-19","cited_by_count":92,"area":null},{"id":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89,"area":null},{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2312.04469","title":"On the Learnability of Watermarks for Language Models","created":"2023-12-07","cited_by_count":81,"area":"safety"},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2310.18491","title":"Publicly-Detectable Watermarking for Language Models","created":"2023-10-27","cited_by_count":76,"area":"safety"},{"id":"2106.06169","title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","created":"2021-06-11","cited_by_count":75,"area":null},{"id":"2203.10321","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","created":"2022-03-19","cited_by_count":75,"area":null},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73,"area":null},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73,"area":null},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71,"area":"safety"},{"id":"2108.01850","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","created":"2021-08-04","cited_by_count":70,"area":null},{"id":"2302.04460","title":"Bag of Tricks for Training Data Extraction from Language Models","created":"2023-02-09","cited_by_count":70,"area":null},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"area":null},{"id":"2402.09497","title":"Instruction Tuning for Secure Code Generation","created":"2024-02-14","cited_by_count":68,"area":null},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67,"area":null},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2205.12558","title":"Gradient-Based Constrained Sampling from Language Models","created":"2022-05-25","cited_by_count":64,"area":null},{"id":"2201.04723","title":"Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents","created":"2022-01-12","cited_by_count":62,"area":null},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59,"area":null},{"id":"2306.02531","title":"PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model","created":"2023-06-05","cited_by_count":58,"area":"diffusion"},{"id":"2109.09707","title":"A Plug-and-Play Method for Controlled Text Generation","created":"2021-09-20","cited_by_count":56,"area":null},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56,"area":"alignment"},{"id":"2105.04623","title":"Improving Factual Consistency of Abstractive Summarization via Question Answering","created":"2021-05-10","cited_by_count":55,"area":null},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2104.05767","title":"Paragraph-level Simplification of Medical Texts","created":"2021-04-12","cited_by_count":53,"area":null},{"id":"2408.17355","title":"Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling","created":"2024-08-30","cited_by_count":52,"area":null},{"id":"2402.10052","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"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":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2301.05843","title":"Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data","created":"2023-01-14","cited_by_count":48,"area":null},{"id":"2404.10859","title":"Forcing Diffuse Distributions out of Language Models","created":"2024-04-16","cited_by_count":48,"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":"2212.10400","title":"Contrastive Learning Reduces Hallucination in Conversations","created":"2022-12-20","cited_by_count":40,"area":null},{"id":"2405.13021","title":"IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues","created":"2024-05-15","cited_by_count":40,"area":"rag"},{"id":"2211.05826","title":"The CRINGE Loss: Learning what language not to model","created":"2022-11-10","cited_by_count":39,"area":null},{"id":"2310.10226","title":"Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective","created":"2023-10-16","cited_by_count":39,"area":null},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2102.08220","title":"Non-Autoregressive Text Generation with Pre-trained Language Models","created":"2021-02-16","cited_by_count":36,"area":null},{"id":"2212.14578","title":"MAUVE Scores for Generative Models: Theory and Practice","created":"2022-12-30","cited_by_count":36,"area":null},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"id":"2402.13512","title":"From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2505.23585","title":"On-Policy RL with Optimal Reward Baseline","created":"2025-05-29","cited_by_count":34,"area":"lr"},{"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":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33,"area":"safety"},{"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":"2305.05976","title":"Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge","created":"2023-05-10","cited_by_count":32,"area":null},{"id":"2102.05126","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","created":"2021-02-09","cited_by_count":31,"area":null},{"id":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31,"area":"safety"}],"next_cursor":"100"}