{"total":135,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830,"area":"agents"},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132,"area":null},{"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":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124,"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":"2102.09130","title":"Entity-level Factual Consistency of Abstractive Text Summarization","created":"2021-02-18","cited_by_count":118,"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":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"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":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"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":"2102.08597","title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66,"area":null},{"id":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62,"area":null},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48,"area":null},{"id":"2312.10007","title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","created":"2023-12-15","cited_by_count":47,"area":null},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"area":null},{"id":"2210.05528","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","created":"2022-10-11","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":"2108.09355","title":"One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles","created":"2021-08-20","cited_by_count":39,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2206.11349","title":"Prompt Injection: Parameterization of Fixed Inputs","created":"2022-05-31","cited_by_count":36,"area":"safety"},{"id":"2105.00816","title":"What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization","created":"2021-04-12","cited_by_count":35,"area":null},{"id":"2310.18659","title":"DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy","created":"2023-10-28","cited_by_count":34,"area":"lr"},{"id":"2203.09313","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","created":"2022-03-17","cited_by_count":31,"area":null},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31,"area":null},{"id":"2502.12378","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","created":"2025-02-17","cited_by_count":31,"area":null},{"id":"2105.11921","title":"Focus Attention: Promoting Faithfulness and Diversity in Summarization","created":"2021-05-25","cited_by_count":30,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"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":"2210.15088","title":"Personalized Dialogue Generation with Persona-Adaptive Attention","created":"2022-10-27","cited_by_count":24,"area":null},{"id":"2305.11482","title":"Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona","created":"2023-05-19","cited_by_count":24,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"area":null},{"id":"2405.17974","title":"Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations","created":"2024-05-28","cited_by_count":20,"area":null},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"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":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2205.13568","title":"Learning Dialogue Representations from Consecutive Utterances","created":"2022-05-26","cited_by_count":17,"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":"2301.04871","title":"Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues","created":"2023-01-12","cited_by_count":17,"area":null},{"id":"2403.04460","title":"Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset","created":"2024-03-07","cited_by_count":16,"area":null},{"id":"2105.03495","title":"Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2109.06471","title":"Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization","created":"2021-09-14","cited_by_count":15,"area":null},{"id":"2106.08364","title":"Unsupervised Enrichment of Persona-grounded Dialog with Background Stories","created":"2021-06-15","cited_by_count":14,"area":null},{"id":"2309.06490","title":"Leveraging Large Language Models for Automated Dialogue Analysis","created":"2023-09-12","cited_by_count":14,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2401.14215","title":"Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement","created":"2024-01-25","cited_by_count":14,"area":null},{"id":"2210.12687","title":"BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets","created":"2022-10-23","cited_by_count":13,"area":null},{"id":"2211.10018","title":"A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach","created":"2022-11-18","cited_by_count":13,"area":null},{"id":"2103.03125","title":"Advances in Multi-turn Dialogue Comprehension: A Survey","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2106.02228","title":"Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency","created":"2021-06-04","cited_by_count":12,"area":null},{"id":"2111.15093","title":"Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description","created":"2021-11-30","cited_by_count":12,"area":null},{"id":"2205.10228","title":"You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2305.11130","title":"SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation","created":"2023-05-18","cited_by_count":11,"area":null},{"id":"2310.18342","title":"MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2109.07713","title":"Transferable Persona-Grounded Dialogues via Grounded Minimal Edits","created":"2021-09-16","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":"2212.09180","title":"Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems","created":"2022-12-18","cited_by_count":9,"area":null},{"id":"2306.08126","title":"PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2109.12702","title":"Extracting and Inferring Personal Attributes from Dialogue","created":"2021-09-26","cited_by_count":8,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2205.09898","title":"Let the Model Decide its Curriculum for Multitask Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2205.02309","title":"Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2608.01619","title":"When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses","created":"2026-08-03","cited_by_count":7,"area":"agents"},{"id":"2110.08438","title":"Unsupervised Natural Language Inference Using PHL Triplet Generation","created":"2021-10-16","cited_by_count":6,"area":null},{"id":"2212.10057","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2305.14755","title":"Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2310.08840","title":"Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2103.09635","title":"SILT: Efficient transformer training for inter-lingual inference","created":"2021-03-17","cited_by_count":5,"area":null},{"id":"2109.04922","title":"Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers","created":"2021-09-10","cited_by_count":5,"area":null},{"id":"2109.06950","title":"Automatically Exposing Problems with Neural Dialog Models","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2208.00329","title":"PASTA: A Dataset for Modeling Participant States in Narratives","created":"2022-07-31","cited_by_count":5,"area":null},{"id":"2207.11862","title":"Improving Bot Response Contradiction Detection via Utterance Rewriting","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2212.10557","title":"DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2306.02980","title":"KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2403.04400","title":"Exploring Continual Learning of Compositional Generalization in NLI","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2404.00557","title":"DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2410.03429","title":"How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics","created":"2024-10-04","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":"2510.01530","title":"LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning","created":"2025-10-02","cited_by_count":4,"area":"lr"},{"id":"2112.02333","title":"LoNLI: An Extensible Framework for Testing Diverse Logical Reasoning Capabilities for NLI","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2112.04195","title":"VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2203.11399","title":"Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection","created":"2022-03-22","cited_by_count":3,"area":null},{"id":"2210.12367","title":"Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation","created":"2022-10-22","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":"2305.13973","title":"Effortless Integration of Memory Management into Open-Domain Conversation Systems","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2311.17376","title":"CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs","created":"2023-11-29","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}],"next_cursor":"100"}