# INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions

arXiv: https://arxiv.org/abs/2207.00746 · HTML: https://mlsanity.com/paper/2207.00746/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 2 Jul 2022.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset](https://mlsanity.com/paper/2011.06623/) (2020)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions](https://mlsanity.com/paper/2109.05794/) (2021)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [DoQA -- Accessing Domain-Specific FAQs via Conversational QA](https://mlsanity.com/paper/2005.01328/) (2020)
- [ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers](https://mlsanity.com/paper/2110.06884/) (2021)
- [Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset](https://mlsanity.com/paper/1912.04639/) (2019)
- [DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization](https://mlsanity.com/paper/2109.04673/) (2021)
- [Ditch the Gold Standard: Re-evaluating Conversational Question Answering](https://mlsanity.com/paper/2112.08812/) (2021)
- [Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity](https://mlsanity.com/paper/2005.00172/) (2020)
- [UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue](https://mlsanity.com/paper/2204.07770/) (2022)

## Built on by (most cited first, 27 of 27)

- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://mlsanity.com/paper/2406.12639/) (2024)
- [Towards Human-centered Proactive Conversational Agents](https://mlsanity.com/paper/2404.12670/) (2024)
- [Task Ambiguity in Humans and Language Models](https://mlsanity.com/paper/2212.10711/) (2022)
- [Asking Clarification Questions to Handle Ambiguity in Open-Domain QA](https://mlsanity.com/paper/2305.13808/) (2023)
- [A Survey on Recent Advances in Conversational Data Generation](https://mlsanity.com/paper/2405.13003/) (2024)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs](https://mlsanity.com/paper/2402.11633/) (2024)
- [Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interaction](https://mlsanity.com/paper/2301.10309/) (2023)
- [UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations](https://mlsanity.com/paper/2507.07030/) (2025)
- [SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment](https://mlsanity.com/paper/2509.03934/) (2025)
- [NewsDialogues: Towards Proactive News Grounded Conversation](https://mlsanity.com/paper/2308.06501/) (2023)
- [Query Understanding in LLM-based Conversational Information Seeking](https://mlsanity.com/paper/2504.06356/) (2025)
- [Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling](https://mlsanity.com/paper/2412.15995/) (2024)
- [Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student Approach](https://mlsanity.com/paper/2503.14167/) (2025)
- [InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning](https://mlsanity.com/paper/2603.05909/) (2026)
- [Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models](https://mlsanity.com/paper/2307.05113/) (2023)
- [DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities](https://mlsanity.com/paper/2507.05750/) (2025)
- [Adaptive Multi-Agent Response Refinement in Conversational Systems](https://mlsanity.com/paper/2511.08319/) (2025)
- [Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight](https://mlsanity.com/paper/2602.15259/) (2026)
- [Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation](https://mlsanity.com/paper/2604.11077/) (2026)
- [Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA](https://mlsanity.com/paper/2602.09552/) (2026)
- [MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks](https://mlsanity.com/paper/2605.20729/) (2026)
- [Measuring Semantic Progress in Multi-turn Dialogue via Information Gain](https://mlsanity.com/paper/2606.12332/) (2026)
- [VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding](https://mlsanity.com/paper/2608.09698/) (2026)
- [HoosierHelp: Benchmarking LLM Agents for Social Service Navigation](https://mlsanity.com/paper/2608.09946/) (2026)
- [Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency](https://mlsanity.com/paper/2608.22266/) (2026)

## Abstract (arXiv)

In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studies either fail to or artificially incorporate such agent-side initiative. This work presents InSCIt, a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains 4.7K user-agent turns from 805 human-human conversations where the agent searches over Wikipedia and either directly answers, asks for clarification, or provides relevant information to address user queries. The data supports two subtasks, evidence passage identification and response generation, as well as a human evaluation protocol to assess model performance. We report results of two systems based on state-of-the-art models of conversational knowledge identification and open-domain question answering. Both systems significantly underperform humans, suggesting ample room for improvement in future studies.