用模型合并技术让检索模型同时胜任单轮和对话搜索，无需重新训练。
Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging
- 通过参数融合（如Model Soup、Slerp）实现零成本模型整合。
- 在零样本条件下，NDCG@3提升最高达15%。
- 适合需要兼顾单轮与对话检索的系统部署场景。
对话式信息检索面临挑战，需考虑对话历史带来的主题变化与指代消解问题。现有方法主要依赖在对话数据集上对单轮检索模型进行微调，或通过多任务学习扩展泛化能力，但这类方法成本高且易产生灾难性遗忘，导致基础单轮检索性能下降。本文提出一种无训练策略——模型合并，构建一个能同时处理单轮与对话检索的统一模型，无需额外微调。我们在标准单轮检索与对话检索数据集上，采用线性和非线性参数融合方法（Model Soup 和 Slerp）进行实验。结果表明，模型合并显著提升了对话检索模型在单轮检索上的表现，并增强了跨任务数据集的泛化能力，在零样本条件下，NDCG@3最高提升15%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。