Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging
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 thi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%Build a protein research copilot with Amazon Bedrock AgentCore →
- PossiblePossibly related (embedding) · 49%EmbedMax →
- PossiblePossibly related (embedding) · 48%stackitcloud/rag-template →
- PossiblePossibly related (embedding) · 46%Evaluating long-term memory limits in stateless LLM chatbots — feedback needed [D] →
- PossiblePossibly related (embedding) · 46%epam/ai-dial-core →
- LinkedLinked via arxiv author · 85%Ahmed Rayane Kebir →
“Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging”
- LinkedLinked via arxiv author · 85%Jose G. Moreno →
“Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging”
- LinkedLinked via arxiv author · 85%Lynda Tamine →
“Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging”