Learning Contextual Retrieval for Robust Conversational Search
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914053759172608 |
|---|---|
| author | Yang, Seunghan Lee, Juntae Bang, Jihwan Shim, Kyuhong Kim, Minsoo Chang, Simyung |
| author_facet | Yang, Seunghan Lee, Juntae Bang, Jihwan Shim, Kyuhong Kim, Minsoo Chang, Simyung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19700 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Contextual Retrieval for Robust Conversational Search Yang, Seunghan Lee, Juntae Bang, Jihwan Shim, Kyuhong Kim, Minsoo Chang, Simyung Information Retrieval 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. |
| title | Learning Contextual Retrieval for Robust Conversational Search |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2509.19700 |