{"total":56,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331,"area":null},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287,"area":null},{"id":"2305.14536","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","created":"2023-05-23","cited_by_count":131,"area":"lr"},{"id":"2401.10225","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","created":"2024-01-18","cited_by_count":90,"area":"rag"},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86,"area":null},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63,"area":null},{"id":"2502.18940","title":"MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors","created":"2025-02-26","cited_by_count":49,"area":null},{"id":"2206.10658","title":"Questions Are All You Need to Train a Dense Passage Retriever","created":"2022-06-21","cited_by_count":47,"area":null},{"id":"2304.08460","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","created":"2023-04-17","cited_by_count":47,"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":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2406.05013","title":"CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search","created":"2024-06-07","cited_by_count":29,"area":null},{"id":"2403.03307","title":"Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots","created":"2024-03-05","cited_by_count":25,"area":"distill"},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23,"area":null},{"id":"2404.13556","title":"ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval","created":"2024-04-21","cited_by_count":19,"area":null},{"id":"2205.12609","title":"Generating Information-Seeking Conversations from Unlabeled Documents","created":"2022-05-25","cited_by_count":17,"area":null},{"id":"2212.10449","title":"Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization","created":"2022-12-20","cited_by_count":17,"area":null},{"id":"2404.03820","title":"CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues","created":"2024-04-04","cited_by_count":15,"area":"lr"},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2402.11178","title":"RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations","created":"2024-02-17","cited_by_count":14,"area":null},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2410.12881","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2407.09897","title":"Cohesive Conversations: Enhancing Authenticity in Multi-Agent Simulated Dialogues","created":"2024-07-13","cited_by_count":11,"area":"agents"},{"id":"2210.08511","title":"CDConv: A Benchmark for Contradiction Detection in Chinese Conversations","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2301.11489","title":"Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation","created":"2023-01-27","cited_by_count":10,"area":"synth"},{"id":"2311.07589","title":"Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2311.15562","title":"Fully Authentic Visual Question Answering Dataset from Online Communities","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2410.23090","title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","created":"2024-10-30","cited_by_count":8,"area":"rag"},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2212.10618","title":"Ontologically Faithful Generation of Non-Player Character Dialogues","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2505.14212","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2309.06748","title":"CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation","created":"2023-09-13","cited_by_count":6,"area":"synth"},{"id":"2502.05467","title":"Position: LLMs Can be Good Tutors in English Education","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2304.14318","title":"q2d: Turning Questions into Dialogs to Teach Models How to Search","created":"2023-04-27","cited_by_count":5,"area":null},{"id":"2308.06501","title":"NewsDialogues: Towards Proactive News Grounded Conversation","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2508.04001","title":"ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2305.10927","title":"Causal Document-Grounded Dialogue Pre-training","created":"2023-05-18","cited_by_count":4,"area":null},{"id":"2403.05814","title":"MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs","created":"2024-03-09","cited_by_count":4,"area":null},{"id":"2212.01739","title":"KPT: Keyword-guided Pre-training for Grounded Dialog Generation","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2308.06507","title":"AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2508.05283","title":"Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2311.10614","title":"A Self-enhancement Approach for Domain-specific Chatbot Training via Knowledge Mining and Digest","created":"2023-11-17","cited_by_count":2,"area":null},{"id":"2406.03703","title":"Synthesizing Conversations from Unlabeled Documents using Automatic Response Segmentation","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2503.11924","title":"REGEN: A Dataset and Benchmarks with Natural Language Critiques and Narratives","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2505.04132","title":"Bringing legal knowledge to the public by constructing a legal question bank using large-scale pre-trained language model","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2507.05750","title":"DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2305.01323","title":"Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2505.20606","title":"Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2510.02331","title":"Synthetic Dialogue Generation for Interactive Conversational Elicitation & Recommendation (ICER)","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.18659","title":"Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2307.00569","title":"SSP: Self-Supervised Post-training for Conversational Search","created":"2023-07-02","cited_by_count":0,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2507.04884","title":"Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions","created":"2025-07-07","cited_by_count":0,"area":"synth"},{"id":"2510.02938","title":"Finding Diamonds in Conversation Haystacks: A Benchmark for Conversational Data Retrieval","created":"2025-10-03","cited_by_count":0,"area":null}],"next_cursor":null}