REVIEW 5 cited by
CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval
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
CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval
read the original abstract
Users often make ambiguous requests that require clarification. We study the problem of asking clarification questions in an information retrieval setting, where systems often face ambiguous search queries and it is challenging to turn the uncertainty in the retrieval model into a natural language question. We present CLARINET, a system that asks informative clarification questions by choosing questions whose answers would maximize certainty in the correct candidate. Our approach works by augmenting a large language model (LLM) to condition on a retrieval distribution, finetuning end-to-end to generate the question that would have maximized the rank of the true candidate at each turn. When evaluated on a real-world retrieval dataset of users searching for books, our system outperforms traditional heuristics such as information gain on retrieval success by 17% and vanilla-prompted LLMs by 39% relative.
Forward citations
Cited by 5 Pith papers
-
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
PaperPilot induces executable DAG workflows for multi-turn literature search and trains via imitation plus preference optimization, raising Hit@5 from 58.0 to 77.0 over a baseline agent.
-
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
PaperPilot induces editable DAG workflows of paper-search operators and, after workflow imitation plus preference training, lifts a 9B multi-turn agent from 58 to 77 Hit@5 while cutting execution errors to 0%.
-
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
Proactive Interactive Reasoning (PIR) teaches LLMs to insert clarification questions into their chain-of-thought, improving simulated task success while cutting reasoning tokens roughly in half.
-
Beyond Conversations: Spatially-Anchored Previews for Intent Disambiguation in LLM-Assisted Geometry Editing in Virtual Reality
Combining clarification questions with in-VR graphical previews in an LLM-assisted geometry editor reduces conversation rounds and steadies task progress compared with clarification alone.
-
Uncertainty-Aware Clarification in LLM Agents with Information Gain
The paper introduces an Information Gain Reward to train clarification behavior in LLM agents, reporting a 3.7% success rate gain over no-clarification baselines in τ-Bench evaluations across five models with minimal ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.