Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910255251718144 |
|---|---|
| author | Baan, Joris Aziz, Wilker Plank, Barbara Fernández, Raquel |
| author_facet | Baan, Joris Aziz, Wilker Plank, Barbara Fernández, Raquel |
| contents | Large language models (LLMs) define a distribution over text, which can be viewed as a probabilistic representation of uncertainty: sampling K responses yields a belief state - responses a model deems plausible. Existing work exploits this representation for narrow tasks like either decoding or selective prediction, and often requires manual interventions, not controlling generation directly. We propose Belief-Augmented Generation (BAG): grounding LLMs in their own belief state via the prompt and letting them reason over these K samples to decide on a conversational strategy: answer, clarify, or abstain. In a multi-turn ambiguous QA setting, we find that LLMs by default rarely clarify or abstain, ignoring uncertainty about the input or facts. BAG improves QA accuracy across six models and yields strategy decisions more faithful to the belief state than prompt-only baselines. Disentangling when to clarify from when to abstain, however, remains challenging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25831 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation Baan, Joris Aziz, Wilker Plank, Barbara Fernández, Raquel Computation and Language Artificial Intelligence Machine Learning Large language models (LLMs) define a distribution over text, which can be viewed as a probabilistic representation of uncertainty: sampling K responses yields a belief state - responses a model deems plausible. Existing work exploits this representation for narrow tasks like either decoding or selective prediction, and often requires manual interventions, not controlling generation directly. We propose Belief-Augmented Generation (BAG): grounding LLMs in their own belief state via the prompt and letting them reason over these K samples to decide on a conversational strategy: answer, clarify, or abstain. In a multi-turn ambiguous QA setting, we find that LLMs by default rarely clarify or abstain, ignoring uncertainty about the input or facts. BAG improves QA accuracy across six models and yields strategy decisions more faithful to the belief state than prompt-only baselines. Disentangling when to clarify from when to abstain, however, remains challenging. |
| title | Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.25831 |