mlsanityData to 7 Oct 2026

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations

arXiv 2507.07030 ↗First posted 9 Jul 2025cs.CL cs.IRcited by 11

Not on the map. Why?

Abstract (arXiv)

The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two different models. This separation restricts the system from leveraging the intrinsic knowledge of the models simultaneously, which cannot ensure the effectiveness of retrieval benefiting the generation. The existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. In this paper, we explore how to unify dense retrieval and response generation for large language models in conversation. We conduct joint fine-tuning with different objectives and design two mechanisms to reduce the inconsistency risks while mitigating data discrepancy. The evaluations on five conversational search datasets demonstrate that our unified model can mutually improve both tasks and outperform the existing baselines.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 45 of its 67 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

45 of 67 references.

References · 45

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2020Scaling Laws for Neural Language Modelscited by 6,411
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  9. 2017Billion-scale similarity search with GPUscited by 2,477
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  11. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  12. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
33 more
  1. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  2. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  3. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  4. 2024Generative Representational Instruction Tuningcited by 227
  5. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  6. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 147
  7. 2022FaithDial: A Faithful Benchmark for Information-Seeking Dialoguecited by 108
  8. 2020Open-Retrieval Conversational Question Answeringcited by 99
  9. 2021TopiOCQA: Open-domain Conversational Question Answering with Topic Switchingcited by 95
  10. 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 74
  11. 2021Few-Shot Conversational Dense Retrievalcited by 71
  12. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
  13. 2021CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learningcited by 68
  14. 2023ConvGQR: Generative Query Reformulation for Conversational Searchcited by 59
  15. 2020Query Resolution for Conversational Search with Limited Supervisioncited by 52
  16. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  17. 2021Contextualized Query Embeddings for Conversational Searchcited by 36
  18. 2024CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Searchcited by 29
  19. 2025Entropy-based Exploration Conduction for Multi-step Reasoningcited by 28
  20. 2022INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactionscited by 27
  21. 2023Learning to Relate to Previous Turns in Conversational Searchcited by 26
  22. 2024Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Checkcited by 24
  23. 2019RefNet: A Reference-aware Network for Background Based Conversationcited by 23
  24. 2024Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversationcited by 23
  25. 2024Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Actioncited by 19
  26. 2022Saving Dense Retriever from Shortcut Dependency in Conversational Searchcited by 18
  27. 2024ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrievalcited by 18
  28. 2024AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignmentcited by 14
  29. 2020Conversations with Search Engines: SERP-based Conversational Response Generationcited by 11
  30. 2024How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrievalcited by 10
  31. 2024Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Searchcited by 10
  32. 2024CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generationcited by 8
  33. 2025Conversational Search: From Fundamentals to Frontiers in the LLM Eracited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2026Revisiting Text Ranking in Deep Researchcited by 7
  2. 2025CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memoriescited by 5
  3. 2026ReAttn: Improving Attention-based Re-ranking via Attention Re-weightingcited by 5
  4. 2025ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrievalcited by 4
  5. 2026Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendationcited by 3
  6. 2026CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generationcited by 1
  7. 2026Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challengescited by 1
  8. 2025Adaptive Personalized Conversational Information Retrievalcited by 0
  9. 2026Re-Rankers as Relevance Judgescited by 0
  10. 2026Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Modelscited by 0
  11. 2026uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Rerankingcited by 0