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

arXiv:2607.08540 · cs.IR, cs.CL · Submitted 2026-07-09 · Read on arXiv

cs.IR, cs.CL

Submitted: 2026-07-09

Updated: 2026-07-09

Comments: Accepted to SIGIR 2026. 6 pages, 3 figures

Journal ref: Proc. of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2026

DOI: 10.1145/3805712.3809939

Code: https://github.com/fengranMark/QRACDR

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Model Merging — 40× in this paper · explained in 2 episodes
• Fine-Tuning — 22× in this paper · explained in 5 episodes
• Information Retrieval — 18× in this paper
• Generalizability — 9× in this paper · explained in 6 episodes
• Catastrophic Forgetting — 6× in this paper · explained in 5 episodes
• Model Soup — 5× in this paper
• Accuracy — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Core — 2× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes

Sources

• Arcee's MergeKit: A Toolkit for Merging Large Language Models
• Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search
• CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
• Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
• UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG