Conversational Search

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 13

All topics

Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging
Jul 9, 2026Ahmed Rayane Kebir, Jose G. Moreno, Lynda TamineConversational Search Information Retrieval
University of Toulouse, IRIT Toulouse, France
When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
Jun 26, 2026Yiling Tao, Shihan Deng, Meiling Tao +3Agentic Search LLM Agent Evaluation
Hunyuan, Tencent · Shenzhen International Graduate School, Tsinghua University
Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search Assistants
Jun 23, 2026Sarthak Harne, Natwar Modani, Debabrata Mahapatra +1E-Commerce Search Conversational Search
2Microsoft Research · 1Adobe Research · 3UC Berkeley
Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues
Jun 3, 2026Hanbo Bi, Zhiqiang Yuan, Chongyang Li +7Multimodal IR Conversational Search
Pattern Recognition Center, WeChat AI, Tencent Inc, China · Aerospace Information Research Institute, Chinese Academy of Sciences
RCEM: Robust Conversational Search EMbedder in Distributional Shift
Jun 1, 2026Kilho Son, Paul Hsu, Cha Zhang +1Distribution Shift Conversational Search
Microsoft Corporation
The Decision to Verify: How Warmth and User Characteristics Shape Reliance on Conversational Agents for Information Search
May 27, 2026Mert Yazan, Frederik Bungaran Ishak Situmeang, Suzan VerberneConversational Search Trust in AI
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
May 27, 2026Xiaohongshu IncAgentic Search Long-Horizon Agent Evaluation
Xiaohongshu Dots Studio & Unipat AI
Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction
May 23, 2026Amsisan Tran, Baogh Le, Tuan Kiet Pham +1Conversational Search Image Retrieval
Amsisan Tran · Baogh Le · Tuan Kiet Pham +1
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
May 20, 2026Junhao Ruan, Abudukeyumu Abudula, Bei Li +8Conversational Search Synthetic Benchmark Generation
School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China · 2Meituan Inc., 3NiuTrans Research, Shenyang, China · 4Tsinghua University, Beijing, China
KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat
May 13, 2026Adrian Cierpka, Mohammad Shafiqul Islam, Johannes Steinhülb +3Conversational Search Information Retrieval
Karlsruhe Institute of Technology
Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking
May 12, 2026David-Maximilian Caraman, Gheorghe Cosmin SilaghiCross-Encoder Reranking Conversational Search
Babeş-Bolyai University Cluj-Napoca, Romania
ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval
May 7, 2026Ke Chen, Shengyuan Han, Yongfeng Huang +4Conversational Search Agentic Retrieval
Institute of Science Tokyo, Japan · Nanjing University of Posts and Telecommunications, Jiangsu, China · The Chinese University of Hong Kong, Hong Kong SAR +3
Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling
May 7, 2026Yiqing Wu, Haoming Li, Guanyu Jiang +4Domain-Adversarial Learning Conversational Search
Bytedance Beijing, China

Jul 9, 2026, cs.IRJ/K move · Enter open · S save

Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging

Ahmed Rayane Kebir, Jose G. Moreno, Lynda Tamine

University of Toulouse, IRIT Toulouse, France

Conversational Search Information Retrieval Model Merging

Open paper AskPDF arXiv

Conversational information retrieval is challenging since it requires the consideration of the conversation history which potentially gives rise to topic shifts and coreference resolution across previous turns. To address these challenges, previous work mainly rely on traditional fine-tuning of ad-hoc retrievers on conversational datasets or extrapolates their generalizability through multi-tasking. However, this mainstream approach is costly - since it requires model re-training - and exhibits catastrophic forgetting, where the model loses its foundational ad-hoc retrieval performance. In this paper, we fill this gap by introducing model merging as a training-free strategy enabling the design of a single retrieval model that operates across both ad-hoc and conversational settings with no additional fine-tuning. We conduct experiments using linear and non-linear parameter-wise merging strategies - namely Model Soup and Slerp - on standard ad-hoc search and conversational retrieval datasets. Our results demonstrate that model merging significantly enhances the ad-hoc search capabilities of conversational retrievers while improving generalizability across task-specific datasets, achieving up to 15% higher NDCG@3 under zero-shot conditions.

Momentum

Related topics

Latest papers 13