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

[2607.08540] Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging Skip to main content Search Submit Donate Log in Computer Science > Information Retrieval arXiv:2607.08540 (cs) [Submitted on 9 Jul 2026] Title: Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging Authors: Ahmed Rayane Kebir , Jose G. Moreno , Lynda Tamine View PDF HTML (experimental) Abstract: 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. Comments: Accepted to SIGIR 2026. 6 pages, 3 figures Subjects: Information Retrieval (cs.IR) ; Computation and Language (cs.CL) ACM classes: H.3.3 Report number: To appear in ACM SIGIR 2026 Cite as: arXiv:2607.08540 [cs.IR] (or arXiv:2607.08540v1 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2607.08540 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proc. of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2026 Related DOI : https://doi.org/10.1145/3805712.3809939 Focus to learn more DOI(s) linking to related resources Submission history From: Ahmed Rayane Kebir [ view email ] [v1] Thu, 9 Jul 2026 14:35:14 UTC (510 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.IR < prev | next > new | recent | 2026-07 Change to browse by: cs cs.CL References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging#677676
• Generative End-to-end Ad Retrieval at Douyin#1144294
• Self-Augmenting Retrieval for Diffusion Language Models#259459
• Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context#1142775
• Users' prompting strategies and ChatGPT's contextual adaptation shape conversational information-seeking experiences.#13687