{"total":1077,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297,"area":"rag"},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392,"area":null},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609,"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":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422,"area":null},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412,"area":null},{"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":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376,"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":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311,"area":null},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263,"area":null},{"id":"2201.06796","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","created":"2022-01-18","cited_by_count":249,"area":null},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225,"area":null},{"id":"2403.14003","title":"Multi-Modal Hallucination Control by Visual Information Grounding","created":"2024-03-20","cited_by_count":208,"area":"mllm"},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202,"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":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158,"area":"rag"},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139,"area":"distill"},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"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":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114,"area":"distill"},{"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":"2305.02437","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","created":"2023-05-03","cited_by_count":103,"area":"rag"},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100,"area":null},{"id":"2106.01702","title":"PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support","created":"2021-06-03","cited_by_count":92,"area":null},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90,"area":null},{"id":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90,"area":null},{"id":"2109.05739","title":"CEM: Commonsense-aware Empathetic Response Generation","created":"2021-09-13","cited_by_count":89,"area":null},{"id":"2203.13560","title":"MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation","created":"2022-03-25","cited_by_count":85,"area":null},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79,"area":null},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79,"area":"alignment"},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"area":null},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76,"area":null},{"id":"2101.07714","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","created":"2021-01-19","cited_by_count":75,"area":null},{"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":"2302.03269","title":"PLACES: Prompting Language Models for Social Conversation Synthesis","created":"2023-02-07","cited_by_count":72,"area":null},{"id":"2009.06978","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","created":"2020-09-15","cited_by_count":68,"area":"alignment"},{"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":"2203.15144","title":"Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support","created":"2022-03-28","cited_by_count":68,"area":null},{"id":"2210.13210","title":"Mutual Information Alleviates Hallucinations in Abstractive Summarization","created":"2022-10-24","cited_by_count":68,"area":null},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","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":"2308.11584","title":"Building Emotional Support Chatbots in the Era of LLMs","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59,"area":null},{"id":"2303.06135","title":"Rewarding Chatbots for Real-World Engagement with Millions of Users","created":"2023-03-10","cited_by_count":59,"area":"alignment"},{"id":"2301.09790","title":"The Next Chapter: A Study of Large Language Models in Storytelling","created":"2023-01-24","cited_by_count":58,"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":"2404.00579","title":"A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)","created":"2024-03-31","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":"2109.09707","title":"A Plug-and-Play Method for Controlled Text Generation","created":"2021-09-20","cited_by_count":56,"area":null},{"id":"2204.12749","title":"Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation","created":"2022-04-27","cited_by_count":56,"area":null},{"id":"2211.05719","title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","created":"2022-11-10","cited_by_count":56,"area":null},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56,"area":null},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2402.13211","title":"Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2304.09582","title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities?","created":"2023-04-19","cited_by_count":54,"area":null},{"id":"2305.18846","title":"Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation","created":"2023-05-30","cited_by_count":54,"area":null},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2305.11707","title":"What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability","created":"2023-05-19","cited_by_count":51,"area":null},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51,"area":null},{"id":"2403.09498","title":"From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News","created":"2024-03-14","cited_by_count":51,"area":null},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50,"area":"mllm"},{"id":"2403.00553","title":"Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores","created":"2024-03-01","cited_by_count":50,"area":null},{"id":"2212.10539","title":"Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?","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":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49,"area":null},{"id":"2106.05555","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","created":"2021-06-10","cited_by_count":48,"area":null},{"id":"2106.00957","title":"RevCore: Review-augmented Conversational Recommendation","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2204.08128","title":"Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation","created":"2022-04-18","cited_by_count":47,"area":null},{"id":"2109.08877","title":"DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation","created":"2021-09-18","cited_by_count":46,"area":null},{"id":"2305.00450","title":"SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support","created":"2023-04-30","cited_by_count":46,"area":null},{"id":"2406.10960","title":"ESCoT: Towards Interpretable Emotional Support Dialogue Systems","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2105.08963","title":"Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence","created":"2021-05-19","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":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2405.08603","title":"A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine","created":"2024-05-14","cited_by_count":45,"area":"mllm"}],"next_cursor":"100"}