{"total":28,"rows":[{"id":"2310.06271","title":"Towards Mitigating Hallucination in Large Language Models via Self-Reflection","created":"2023-10-10","cited_by_count":81,"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":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37,"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":"2401.00690","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","created":"2024-01-01","cited_by_count":27,"area":null},{"id":"2301.10416","title":"AI vs. Human -- Differentiation Analysis of Scientific Content Generation","created":"2023-01-24","cited_by_count":21,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2406.18365","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","created":"2024-06-26","cited_by_count":19,"area":null},{"id":"2310.08394","title":"Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization","created":"2023-10-12","cited_by_count":18,"area":null},{"id":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","cited_by_count":17,"area":null},{"id":"2305.08566","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","created":"2023-05-15","cited_by_count":16,"area":null},{"id":"2404.13919","title":"Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models","created":"2024-04-22","cited_by_count":15,"area":null},{"id":"2304.14106","title":"ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time","created":"2023-04-27","cited_by_count":12,"area":null},{"id":"2311.09648","title":"Event Causality Is Key to Computational Story Understanding","created":"2023-11-16","cited_by_count":11,"area":null},{"id":"2310.14892","title":"Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2306.10317","title":"Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation","created":"2023-06-17","cited_by_count":7,"area":null},{"id":"2307.06869","title":"DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2404.19563","title":"RepEval: Effective Text Evaluation with LLM Representation","created":"2024-04-30","cited_by_count":6,"area":null},{"id":"2406.15227","title":"A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation","created":"2024-06-21","cited_by_count":6,"area":null},{"id":"2308.01327","title":"Careful Whisper -- leveraging advances in automatic speech recognition for robust and interpretable aphasia subtype classification","created":"2023-08-02","cited_by_count":5,"area":null},{"id":"2412.07334","title":"Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2305.17819","title":"Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2505.19660","title":"Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2411.00034","title":"Is Our Chatbot Telling Lies? Assessing Correctness of an LLM-based Dutch Support Chatbot","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2504.20849","title":"JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2512.19620","title":"Exploring the features used for summary evaluation by Human and GPT","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2609.34240","title":"Coherence-Aware Distributional Evaluation of Open-Ended Text Generation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}