{"total":47,"rows":[{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264,"area":null},{"id":"2209.14958","title":"Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals","created":"2022-09-29","cited_by_count":191,"area":null},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124,"area":null},{"id":"2307.02762","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","created":"2023-07-06","cited_by_count":114,"area":null},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109,"area":null},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59,"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":"2306.01200","title":"Multi-Dimensional Evaluation of Text Summarization with In-Context Learning","created":"2023-06-01","cited_by_count":44,"area":null},{"id":"2211.11875","title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","created":"2022-11-21","cited_by_count":40,"area":null},{"id":"2209.03392","title":"Investigating Reasons for Disagreement in Natural Language Inference","created":"2022-09-07","cited_by_count":29,"area":null},{"id":"2204.09867","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","created":"2022-04-21","cited_by_count":25,"area":null},{"id":"2405.05894","title":"Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons","created":"2024-05-09","cited_by_count":22,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2109.11292","title":"Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System","created":"2021-09-23","cited_by_count":18,"area":null},{"id":"2208.10816","title":"Improving Personality Consistency in Conversation by Persona Extending","created":"2022-08-23","cited_by_count":17,"area":null},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16,"area":null},{"id":"2505.00268","title":"Consistency in Language Models: Current Landscape, Challenges, and Future Directions","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2305.02747","title":"Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation","created":"2023-05-04","cited_by_count":11,"area":null},{"id":"2108.12465","title":"Code-switched inspired losses for generic spoken dialog representations","created":"2021-08-27","cited_by_count":10,"area":null},{"id":"2210.08511","title":"CDConv: A Benchmark for Contradiction Detection in Chinese Conversations","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2501.12011","title":"Reference-free Evaluation Metrics for Text Generation: A Survey","created":"2025-01-21","cited_by_count":9,"area":null},{"id":"2112.05417","title":"Unsupervised Editing for Counterfactual Stories","created":"2021-12-10","cited_by_count":8,"area":null},{"id":"2305.03088","title":"Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","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":"2205.14748","title":"Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition","created":"2022-05-29","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2209.00876","title":"Dialogue Evaluation with Offline Reinforcement Learning","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2212.08992","title":"PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment","created":"2022-12-18","cited_by_count":3,"area":null},{"id":"2401.10353","title":"Inconsistent dialogue responses and how to recover from them","created":"2024-01-18","cited_by_count":3,"area":null},{"id":"2505.24826","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2601.10085","title":"CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2108.01369","title":"How to Evaluate Your Dialogue Models: A Review of Approaches","created":"2021-08-03","cited_by_count":2,"area":null},{"id":"2204.06970","title":"Can Visual Dialogue Models Do Scorekeeping? Exploring How Dialogue Representations Incrementally Encode Shared Knowledge","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2208.08094","title":"SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation","created":"2022-08-17","cited_by_count":2,"area":null},{"id":"2211.07591","title":"Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2404.07836","title":"Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2605.27345","title":"MATCHA: Matching Text via Contrastive Semantic Alignment","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2403.11509","title":"DEE: Dual-stage Explainable Evaluation Method for Text Generation","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2405.15110","title":"CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2406.18133","title":"ConvoCache: Smart Re-Use of Chatbot Responses","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2410.20174","title":"A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation","created":"2024-10-26","cited_by_count":0,"area":null},{"id":"2508.02931","title":"Can LLMs Generate High-Quality Task-Specific Conversations?","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2510.15972","title":"Quantum NLP models on Natural Language Inference","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2609.31719","title":"Distributional Metrics for Evaluating Spoken Conversational Systems","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}