# Learning Contextual Retrieval for Robust Conversational Search

arXiv: https://arxiv.org/abs/2509.19700 · HTML: https://mlsanity.com/paper/2509.19700/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2025.

## Built on by (most cited first, 7 of 7)

- [LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval](https://mlsanity.com/paper/2603.01425/) (2026)
- [Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory](https://mlsanity.com/paper/2603.16862/) (2026)
- [ITER: Interaction-Aware Retrieval for Agentic Search](https://mlsanity.com/paper/2608.27912/) (2026)
- [Feedback Adaptation for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.06647/) (2026)
- [RCEM: Robust Conversational Search EMbedder in Distributional Shift](https://mlsanity.com/paper/2606.01697/) (2026)
- [Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging](https://mlsanity.com/paper/2607.08540/) (2026)
- [RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval](https://mlsanity.com/paper/2610.17673/) (2026)

## Abstract (arXiv)

Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers. While query rewriting techniques improve clarity, they often incur significant computational cost due to additional autoregressive steps. Moreover, although LLM-based retrievers demonstrate strong performance, they are not explicitly optimized to track user intent in multi-turn settings, often failing under topic drift or contextual ambiguity. To address these limitations, we propose ContextualRetriever, a novel LLM-based retriever that directly incorporates conversational context into the retrieval process. Our approach introduces: (1) a context-aware embedding mechanism that highlights the current query within the dialogue history; (2) intent-guided supervision based on high-quality rewritten queries; and (3) a training strategy that preserves the generative capabilities of the base LLM. Extensive evaluations across multiple conversational search benchmarks demonstrate that ContextualRetriever significantly outperforms existing methods while incurring no additional inference overhead.