mlsanityData to 7 Oct 2026

Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems

arXiv 2403.11413 ↗First posted 18 Mar 2024cs.CLcited by 7

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

When interacting with Retrieval-Augmented Generation (RAG)-based conversational agents, the users must carefully craft their queries to be understood correctly. Yet, understanding the system's capabilities can be challenging for the users, leading to ambiguous questions that necessitate further clarification. This work aims to bridge the gap by developing a suggestion question generator. To generate suggestion questions, our approach involves utilizing dynamic context, which includes both dynamic few-shot examples and dynamically retrieved contexts. Through experiments, we show that the dynamic contexts approach can generate better suggestion questions as compared to other prompting approaches.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 12 of its 15 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

12 of 15 references.

References · 12

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2018CoQA: A Conversational Question Answering Challengecited by 674
  4. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  5. 2018QuAC : Question Answering in Contextcited by 379
  6. 2020Injecting Numerical Reasoning Skills into Language Modelscited by 133
  7. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 115
  8. 2018Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Informationcited by 110
  9. 2023A Survey on Asking Clarification Questions Datasets in Conversational Systemscited by 28
  10. 2021ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphscited by 22
  11. 2023Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialoguescited by 7
  12. 2021Conversational Search with Mixed-Initiative -- Asking Good Clarification Questions backed-up by Passage Retrievalcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluationcited by 8
  2. 2025DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generationcited by 7
  3. 2025Query Understanding in LLM-based Conversational Information Seekingcited by 4
  4. 2025Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistancecited by 3
  5. 2025Reliable Conversational Agents under ASP Control that Understand Natural Languagecited by 0
  6. 2026Query Suggestion for Retrieval-Augmented Generation via Dynamic In-Context Learningcited by 0
  7. 2026An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Toward Conversational Agents with Context and Time Sensitive Long-term Memory
  2. 2024Adaptive Retrieval-Augmented Generation for Conversational Systems
  3. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
  4. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems
  5. 2026Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA
  6. 2024Introducing a new hyper-parameter for RAG: Context Window Utilization
  7. 2024Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations
  8. 2024Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check