{"total":164,"rows":[{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"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":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172,"area":null},{"id":"2405.07437","title":"Evaluation of Retrieval-Augmented Generation: A Survey","created":"2024-05-13","cited_by_count":146,"area":"rag"},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2306.07906","title":"WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences","created":"2023-06-13","cited_by_count":100,"area":null},{"id":"2107.01294","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","created":"2021-07-02","cited_by_count":89,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"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":"2203.12990","title":"Generating Scientific Claims for Zero-Shot Scientific Fact Checking","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2306.03100","title":"Rethinking Model Evaluation as Narrowing the Socio-Technical Gap","created":"2023-06-01","cited_by_count":56,"area":"lr"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2411.16508","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","created":"2024-11-25","cited_by_count":55,"area":"wm"},{"id":"2306.05783","title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation","created":"2023-06-09","cited_by_count":52,"area":null},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38,"area":null},{"id":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2407.21065","title":"LawLLM: Law Large Language Model for the US Legal System","created":"2024-07-27","cited_by_count":37,"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":"2403.07311","title":"Knowledge Graph Large Language Model (KG-LLM) for Link Prediction","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2204.00447","title":"Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation","created":"2022-04-01","cited_by_count":33,"area":null},{"id":"2205.06828","title":"Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications","created":"2022-05-13","cited_by_count":32,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2203.12258","title":"Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View","created":"2022-03-23","cited_by_count":31,"area":null},{"id":"2505.12201","title":"How Reliable is Multilingual LLM-as-a-Judge?","created":"2025-05-18","cited_by_count":30,"area":null},{"id":"2507.21028","title":"Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation","created":"2025-07-28","cited_by_count":30,"area":"agents"},{"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":"2312.13585","title":"Speech Translation with Large Language Models: An Industrial Practice","created":"2023-12-21","cited_by_count":28,"area":null},{"id":"2212.10180","title":"IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages","created":"2022-12-20","cited_by_count":27,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2310.19792","title":"The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics","created":"2023-10-30","cited_by_count":23,"area":null},{"id":"2108.13349","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","created":"2021-08-30","cited_by_count":22,"area":null},{"id":"2110.00687","title":"Investigating Robustness of Dialog Models to Popular Figurative Language Constructs","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2406.06357","title":"MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows","created":"2024-06-10","cited_by_count":19,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2211.01635","title":"Revisiting Grammatical Error Correction Evaluation and Beyond","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2211.07126","title":"Discharge Summary Hospital Course Summarisation of In Patient Electronic Health Record Text with Clinical Concept Guided Deep Pre-Trained Transformer Models","created":"2022-11-14","cited_by_count":18,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2411.05375","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2401.00437","title":"BatchEval: Towards Human-like Text Evaluation","created":"2023-12-31","cited_by_count":17,"area":null},{"id":"2406.05707","title":"QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation","created":"2024-06-09","cited_by_count":17,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"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":"2402.15589","title":"LLMs as Meta-Reviewers' Assistants: A Case Study","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2405.09935","title":"DEBATE: Devil's Advocate-Based Assessment and Text Evaluation","created":"2024-05-16","cited_by_count":16,"area":null},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16,"area":null},{"id":"2106.03816","title":"Diversity driven Query Rewriting in Search Advertising","created":"2021-06-07","cited_by_count":15,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"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":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"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":"2304.01662","title":"Cross-Domain Image Captioning with Discriminative Finetuning","created":"2023-04-04","cited_by_count":14,"area":null},{"id":"2312.10355","title":"CoAScore: Chain-of-Aspects Prompting for NLG Evaluation","created":"2023-12-16","cited_by_count":14,"area":null},{"id":"2103.10918","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","created":"2021-03-19","cited_by_count":13,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2211.00727","title":"Quantum Natural Language Generation on Near-Term Devices","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2211.16259","title":"Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text Corpora","created":"2022-11-29","cited_by_count":11,"area":null},{"id":"2305.15067","title":"Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2406.12319","title":"The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators","created":"2024-06-18","cited_by_count":11,"area":null},{"id":"2111.13463","title":"Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems","created":"2021-11-26","cited_by_count":10,"area":null},{"id":"2203.06063","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2205.08478","title":"An Evaluation Framework for Legal Document Summarization","created":"2022-05-17","cited_by_count":10,"area":null},{"id":"2409.07085","title":"Understanding Knowledge Drift in LLMs through Misinformation","created":"2024-09-11","cited_by_count":10,"area":null},{"id":"2208.04163","title":"Abstractive Meeting Summarization: A Survey","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2303.08991","title":"DeltaScore: Fine-Grained Story Evaluation with Perturbations","created":"2023-03-15","cited_by_count":9,"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":"2205.09314","title":"Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2205.12467","title":"R2D2: Robust Data-to-Text with Replacement Detection","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2210.10332","title":"Revision Transformers: Instructing Language Models to Change their Values","created":"2022-10-19","cited_by_count":8,"area":null},{"id":"2504.07749","title":"NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark","created":"2025-04-10","cited_by_count":8,"area":null},{"id":"2311.16764","title":"Radiology-Aware Model-Based Evaluation Metric for Report Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2406.06399","title":"Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue","created":"2024-06-10","cited_by_count":7,"area":null},{"id":"2501.08102","title":"Consistency of Responses and Continuations Generated by Large Language Models on Social Media","created":"2025-01-14","cited_by_count":7,"area":null},{"id":"2504.08697","title":"LLMs as Span Annotators: A Comparative Study of LLMs and Humans","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2106.02833","title":"Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation","created":"2021-06-05","cited_by_count":6,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2305.05471","title":"Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2403.14275","title":"Is Reference Necessary in the Evaluation of NLG Systems? When and Where?","created":"2024-03-21","cited_by_count":6,"area":null},{"id":"2405.14646","title":"Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models","created":"2024-05-23","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":"2411.03012","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2208.08241","title":"ILLUME: Rationalizing Vision-Language Models through Human Interactions","created":"2022-08-17","cited_by_count":5,"area":"mllm"},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","cited_by_count":5,"area":null},{"id":"2210.07228","title":"Language Model Decoding as Likelihood-Utility Alignment","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2303.08389","title":"PR-MCS: Perturbation Robust Metric for MultiLingual Image Captioning","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2306.07554","title":"HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2307.00963","title":"Challenges in Domain-Specific Abstractive Summarization and How to Overcome them","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2401.04518","title":"The Critique of Critique","created":"2024-01-09","cited_by_count":5,"area":null},{"id":"2406.18116","title":"BADGE: BADminton report Generation and Evaluation with LLM","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2412.15189","title":"Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2503.16423","title":"GAEA: A Geolocation Aware Conversational Assistant","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2510.09404","title":"Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges","created":"2025-10-10","cited_by_count":5,"area":"agents"},{"id":"2210.13025","title":"On the Effectiveness of Automated Metrics for Text Generation Systems","created":"2022-10-24","cited_by_count":4,"area":null}],"next_cursor":"100"}