# Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation

arXiv: https://arxiv.org/abs/2402.11827 · HTML: https://mlsanity.com/paper/2402.11827/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 30 of 36)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [Aligning Large Language Models through Synthetic Feedback](https://mlsanity.com/paper/2305.13735/) (2023)
- [Few-Shot Conversational Dense Retrieval](https://mlsanity.com/paper/2105.04166/) (2021)
- [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)

## Built on by (most cited first, 23 of 23)

- [Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning](https://mlsanity.com/paper/2503.24289/) (2025)
- [CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search](https://mlsanity.com/paper/2406.05013/) (2024)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval](https://mlsanity.com/paper/2404.13556/) (2024)
- [Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers](https://mlsanity.com/paper/2406.10991/) (2024)
- [AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment](https://mlsanity.com/paper/2407.01965/) (2024)
- [Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications](https://mlsanity.com/paper/2501.02460/) (2025)
- [UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations](https://mlsanity.com/paper/2507.07030/) (2025)
- [ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval](https://mlsanity.com/paper/2508.04001/) (2025)
- [Crafting the Path: Robust Query Rewriting for Information Retrieval](https://mlsanity.com/paper/2407.12529/) (2024)
- [Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities](https://mlsanity.com/paper/2409.15290/) (2024)
- [ICR: Iterative Clarification and Rewriting for Conversational Search](https://mlsanity.com/paper/2509.05100/) (2025)
- [Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback](https://mlsanity.com/paper/2410.21242/) (2024)
- [AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation](https://mlsanity.com/paper/2506.01381/) (2025)
- [Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01158/) (2024)
- [Adaptive Personalized Conversational Information Retrieval](https://mlsanity.com/paper/2508.08634/) (2025)
- [Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search](https://mlsanity.com/paper/2604.06771/) (2026)
- [References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation](https://mlsanity.com/paper/2505.06552/) (2025)
- [Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions](https://mlsanity.com/paper/2507.04884/) (2025)
- [When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning](https://mlsanity.com/paper/2601.21208/) (2026)
- [Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval](https://mlsanity.com/paper/2608.06614/) (2026)
- [Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization](https://mlsanity.com/paper/2608.09043/) (2026)
- [CompCQR: Compositional Query Generation for Training-Free Conversational Search](https://mlsanity.com/paper/2609.14646/) (2026)

## Abstract (arXiv)

Conversational search, unlike single-turn retrieval tasks, requires understanding the current question within a dialogue context. The common approach of rewrite-then-retrieve aims to decontextualize questions to be self-sufficient for off-the-shelf retrievers, but most existing methods produce sub-optimal query rewrites due to the limited ability to incorporate signals from the retrieval results. To overcome this limitation, we present a novel framework RetPO (Retriever's Preference Optimization), which is designed to optimize a language model (LM) for reformulating search queries in line with the preferences of the target retrieval systems. The process begins by prompting a large LM to produce various potential rewrites and then collects retrieval performance for these rewrites as the retrievers' preferences. Through the process, we construct a large-scale dataset called RF collection, containing Retrievers' Feedback on over 410K query rewrites across 12K conversations. Furthermore, we fine-tune a smaller LM on this dataset to align it with the retrievers' feedback. Our resulting model demonstrates superiority on two benchmarks, surpassing the previous state-of-the-art performance of rewrite-then-retrieve approaches.