# DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search

arXiv: https://arxiv.org/abs/2410.14609 · HTML: https://mlsanity.com/paper/2410.14609/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 38 of its 66 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [Few-Shot Conversational Dense Retrieval](https://mlsanity.com/paper/2105.04166/) (2021)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting](https://mlsanity.com/paper/2310.09716/) (2023)
- [CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning](https://mlsanity.com/paper/2112.08558/) (2021)
- [ConvGQR: Generative Query Reformulation for Conversational Search](https://mlsanity.com/paper/2305.15645/) (2023)
- [Minimizing FLOPs to Learn Efficient Sparse Representations](https://mlsanity.com/paper/2004.05665/) (2020)
- [CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search](https://mlsanity.com/paper/2406.05013/) (2024)
- [An Efficiency Study for SPLADE Models](https://mlsanity.com/paper/2207.03834/) (2022)
- [IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance](https://mlsanity.com/paper/2311.09820/) (2023)
- [A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE](https://mlsanity.com/paper/2403.10407/) (2024)
- [TREC iKAT 2023: A Test Collection for Evaluating Conversational and Interactive Knowledge Assistants](https://mlsanity.com/paper/2405.02637/) (2024)
- [A Static Pruning Study on Sparse Neural Retrievers](https://mlsanity.com/paper/2304.12702/) (2023)
- [Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Search](https://mlsanity.com/paper/2407.20189/) (2024)

## Built on by (most cited first, 9 of 9)

- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [Enhancing Lexicon-Based Text Embeddings with Large Language Models](https://mlsanity.com/paper/2501.09749/) (2025)
- [Investigating LLM Variability in Personalized Conversational Information Retrieval](https://mlsanity.com/paper/2510.03795/) (2025)
- [On the Challenges and Opportunities of Learned Sparse Retrieval for Code](https://mlsanity.com/paper/2603.22008/) (2026)
- [GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing](https://mlsanity.com/paper/2605.02489/) (2026)
- [Adaptive Personalized Conversational Information Retrieval](https://mlsanity.com/paper/2508.08634/) (2025)
- [Cross-Sensory Brain Passage Retrieval: Scaling Beyond Visual to Audio](https://mlsanity.com/paper/2601.14001/) (2026)
- [uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking](https://mlsanity.com/paper/2606.11945/) (2026)
- [RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval](https://mlsanity.com/paper/2610.17673/) (2026)

## Abstract (arXiv)

Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have significantly enhanced CS by enabling query rewriting based on conversational context. However, employing LLMs during inference poses efficiency challenges. Existing solutions mitigate this issue by distilling embeddings derived from human-rewritten queries, focusing primarily on learning the context modeling task. These methods, however, often separate the contrastive retrieval task from the distillation process, treating it as an independent loss term. To overcome these limitations, we introduce DiSCo (Distillation of Sparse Conversational retrieval), a novel approach that unifies retrieval and context modeling through a relaxed distillation objective. Instead of relying exclusively on representation learning, our method distills similarity scores between conversations and documents, providing more freedom in the representation space and better leveraging the contrastive nature of document relevance. Extensive experiments on Learned Sparse Retrieval (LSR) across five CS datasets demonstrate that DiSCo achieves substantial improvements in both in-domain and out-of-domain retrieval tasks, achieving up to a six-point gain in recall for out-of-domain datasets over state-of-the-art methods. Additionally, DiSCo employs a multi-teacher distillation strategy, using multiple LLMs as teachers, further enhancing performance and surpassing the individual teachers in in-domain settings. Furthermore, analysis of model sparsity reveals that DiSCo allows for more effective control over the sparsity of the trained models.