# Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering

arXiv: https://arxiv.org/abs/2503.22303 · HTML: https://mlsanity.com/paper/2503.22303/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)
- 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, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Conversational Information Seeking](https://mlsanity.com/paper/2201.08808/) (2022)
- [ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval](https://mlsanity.com/paper/2404.13556/) (2024)
- [Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2105.04850/) (2021)
- [Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers](https://mlsanity.com/paper/2406.10991/) (2024)
- [Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation](https://mlsanity.com/paper/2310.13505/) (2023)
- [CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval](https://mlsanity.com/paper/2301.04413/) (2023)
- [UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers](https://mlsanity.com/paper/2410.20163/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Survey on LLM-based Conversational User Simulation](https://mlsanity.com/paper/2604.24977/) (2026)
- [Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation](https://mlsanity.com/paper/2505.17391/) (2025)
- [A Survey of the State-of-the-Art in Conversational Question Answering Systems](https://mlsanity.com/paper/2509.05716/) (2025)

## Abstract (arXiv)

Conversational Question Answering (ConvQA) involves multiple subtasks, i) to understand incomplete questions in their context, ii) to retrieve relevant information, and iii) to generate answers. This work presents PRAISE, a pipeline-based approach for ConvQA that trains LLM adapters for each of the three subtasks. As labeled training data for individual subtasks is unavailable in practice, PRAISE learns from its own generations using the final answering performance as feedback signal without human intervention and treats intermediate information, like relevant evidence, as weakly labeled data. We apply Direct Preference Optimization by contrasting successful and unsuccessful samples for each subtask. In our experiments, we show the effectiveness of this training paradigm: PRAISE shows improvements per subtask and achieves new state-of-the-art performance on a popular ConvQA benchmark, by gaining 15.5 percentage points increase in precision over baselines.