Pith. sign in

REVIEW 12 cited by

STaR-GATE: Teaching Language Models to Ask Clarifying Questions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.19154 v3 pith:FIAV5MAS submitted 2024-03-28 cs.CL cs.AI

classification cs.CLcs.AI
keywords questionslanguagemodelquestionerresponsesbettermodelspreferences
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

When prompting language models to complete a task, users often leave important aspects unsaid. While asking questions could resolve this ambiguity (GATE; Li et al., 2023), models often struggle to ask good questions. We explore a language model's ability to self-improve (STaR; Zelikman et al., 2022) by rewarding the model for generating useful questions-a simple method we dub STaR-GATE. We generate a synthetic dataset of 25,500 unique persona-task prompts to simulate conversations between a pretrained language model-the Questioner-and a Roleplayer whose preferences are unknown to the Questioner. By asking questions, the Questioner elicits preferences from the Roleplayer. The Questioner is iteratively finetuned on questions that increase the probability of high-quality responses to the task, which are generated by an Oracle with access to the Roleplayer's latent preferences. After two iterations of self-improvement, the Questioner asks better questions, allowing it to generate responses that are preferred over responses from the initial model on 72% of tasks. Our results indicate that teaching a language model to ask better questions leads to better personalized responses.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Interactive Task Alignment as a POMDP

    cs.AI 2026-07 conditional novelty 7.0 of 10

    Under ambiguous user requests, current LLMs recover the intended task only 22–32% of the time, well below human accuracy of 48%, and post-training only partially closes the gap.

  2. Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulation in Complex Task Resolution

    cs.MA 2026-08 conditional novelty 6.0 of 10

    An eight-agent question-asking system that front-loads intent clarification produced more complete prompts, higher-rated outputs, and single-turn task completion in a four-person pilot, with unstable effect sizes.

  3. SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A 4B model fine-tuned on a 9,203-step LLM-annotated corpus with a single tunable threshold yields a three-way EXECUTE/ASK/REFUSE guard that beats zero-shot baselines on in-distribution and held-out agent actions.

  4. Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A training method using reinforcement learning and answerability heuristics lets small language models actively ask for missing math details and then solve problems, raising accuracy on the new GSM-MC benchmark from 0...

  5. The Curious Language Model: Strategic Test-Time Information Acquisition

    cs.LG 2025-06 conditional novelty 6.0 of 10

    CuriosiTree is a greedy tree-search policy that lets LLMs select cost-effective information-gathering actions at test time, outperforming baselines in a simulated clinical diagnosis environment.

  6. Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment

    cs.CL 2025-04 conditional novelty 6.0 of 10

    Persona-judge applies speculative decoding between two preference-prompted copies of the same LLM to achieve training-free personalized alignment.

  7. CollabLLM: From Passive Responders to Active Collaborators

    cs.AI 2025-02 conditional novelty 6.0 of 10

    CollabLLM computes multiturn-aware rewards by forward-simulating future user turns, then fine-tunes the LLM with RL to ask clarifying questions and guide users to their goals.

  8. DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models

    cs.CL 2026-08 conditional novelty 5.0 of 10

    A self-play dialogue framework with a self-trained questioner improves zero-shot named entity recognition over basic prompting, but not consistently over the strongest existing methods.

  9. Bridging Gaps Between Student and Expert Evaluations of AI-Generated Programming Hints

    cs.CY 2025-09 conditional novelty 5.0 of 10

    Expert rubric ratings overstate student-perceived helpfulness of AI-generated hints in 26.6% of cases, with mismatch reasons grouped into five categories and preliminary fixes proposed.

  10. Referential ambiguity and clarification requests: comparing human and LLM behaviour

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Humans seldom ask clarification questions for referential ambiguity, while LLMs ask them more often, and reasoning prompts increase LLM question frequency and relevance.

  11. Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions

    cs.AI 2025-07 conditional novelty 4.0 of 10

    A fine-tuned classifier and question generator let a small coding assistant detect under-specified prompts and ask for clarification, which users rated better than a baseline in a small study.

  12. AI and the Future of Digital Public Squares

    cs.CY 2024-12 unverdicted novelty 3.0 of 10

    A multi-stakeholder agenda argues that LLM-enabled collective dialogue, bridging, moderation, and proof-of-humanity tools can strengthen digital public squares if paired with research and safeguards.

Pith tools