Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing

• URL: http://arxiv.org/abs/2607.01964v1
• Date: Thu, 02 Jul 2026 09:57:52 GMT
• Title: Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing
• Abstract summary: Rewriting inputs to improve frozen downstream models has become a common strategy in modern NLP pipelines.<n>In this work, we revisit this idea under realistic deployment conditions, where no clarification supervision is available.<n>A best-of-8 rewriting analysis reveals a practical ceiling: a large fraction of errors are not repairable through input alone.
• Score: 16.51635619165348
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Rewriting inputs to improve frozen downstream models has become a common strategy in modern NLP pipelines. Prior work on incremental dialogue discourse parsing (DDP) shows that supervised clarification models can rewrite fragmentary or underspecified utterances, such as resolving ellipsis or references, to improve parsing accuracy. In this work, we revisit this idea under realistic deployment conditions, where no clarification supervision is available and the clarifier must rely on zero-shot prompting or feedback from a frozen parser. Across three Segmented Discourse Representation Theory (SDRT) datasets and multiple parsers, we find that last-utterance clarification is far less reliable than suggested by supervised settings. Parser-agnostic rewriting often introduces more regressions than repairs, as edits that enable fixes also disrupt discourse cues relied upon by the parser. A best-of-8 rewriting analysis further reveals a practical ceiling: a large fraction of errors are not repairable through input rewriting alone. A parser-aware clarifier trained with GRPO reduces regressions by up to 37% by learning conservative abstention, yet still fails to produce selectivity-aware clarifications that consistently improve parsing. Together, these findings recast clarification as a selective intervention problem. We identify rewritability prediction, deciding whether an utterance is repairable before intervention, as the key missing capability for input-side optimization of frozen discourse parsers, and a critical direction for improving agentic pipelines more broadly.

Related papers

• RetroThinker: Enabling Retrospective Thinking in Speech LLMs [42.95471264630473]
  Speech large language models (SpeechLLMs) lag behind text-only LLMs on complex reasoning tasks.<n>We introduce RetroThinker, a multi-stage post-training framework that equips the Moshi model to self-verify and forward-correct CoT steps during inference.<n>RetroThinker significantly improves the accuracy-latency trade-off over non-retrospective baselines, achieving an 11% absolute accuracy gain at a comparable latency.
  arXiv  Detail & Related papers  (2026-09-10T17:41:53Z)
• InsightSeg: Reusing Correction Insights for Guideline-Consistent Segmentation [4.501547677532766]
  We introduce InsightSeg, an episodic memory mechanism that converts successful correction episodes into reusable, visually grounded insights.<n>Across and Cityscapes, InsightSeg improves both first-pass and final guideline-consistent segmentation performance while requiring fewer refinement steps.
  arXiv  Detail & Related papers  (2026-09-02T02:22:35Z)
• Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach [58.15427952222424]
  General-purpose text embeddings are widely deployed for such tasks, but broad semantic similarity can place semantically similar yet task-distinct examples.<n>We introduce Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings.
  arXiv  Detail & Related papers  (2026-08-15T13:19:25Z)
• Reflective Prompt Tuning through Language Model Function-Calling [16.552558967042312]
  Reflective Prompt Tuning (RPT) is a framework that simulates the iterative workflow of human prompt engineers.<n>RPT improves over initial prompts by up to 12.9 points, remains competitive with state of the art, and improves confidence calibration.<n>Our analyses show that RPT is especially effective on multi-hop and mathematical reasoning.
  arXiv  Detail & Related papers  (2026-05-20T22:21:29Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance [4.655159257282135]
  Large Language Models (LLMs) often struggle to perform targeted refutation and maintain accurate factual grounding when used directly for rebuttal generation.<n>We introduce DEFEND an LLM based tool designed to explicitly execute the underlying reasoning process of automated rebuttal generation.<n>As opposed to writing the rebuttals from scratch, the author needs to only drive the reasoning process with minimal intervention.
  arXiv  Detail & Related papers  (2026-03-28T18:12:31Z)
• Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval [0.11280931253550518]
  We show that prompt-only rewriting can be harmful in well-optimized verticals.<n>We identify a consistent mechanism: rewritten terms co-occur with reduced lexical alignment.<n>We suggest that domain-adaptive post-training is a safer strategy when supervision or implicit feedback is available.
  arXiv  Detail & Related papers  (2026-03-02T10:40:10Z)
• Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution [79.98699884805636]
  Reasoning Execution by Multiple Listeners (REMUL) is a multi-party reinforcement learning approach.<n>REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful.<n>Speakers are rewarded for producing reasoning that is clear to listeners.
  arXiv  Detail & Related papers  (2026-02-18T02:55:55Z)
• Constraint-Rectified Training for Efficient Chain-of-Thought [60.52883907721588]
  Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)<n>While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking.<n>Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy.
  arXiv  Detail & Related papers  (2026-02-13T02:13:45Z)
• DRES: Benchmarking LLMs for Disfluency Removal [27.083825614818135]
  Disfluencies, such as "um," "uh," interjections, parentheticals, and edited statements, remain a persistent challenge for speech-driven systems.<n>Disfluency Removal Evaluation Suite, a controlled text-level benchmark, establishes a reproducible semantic upper bound for this task.<n>DRES builds on human-annotated Switchboard transcripts, isolating disfluency removal from ASR errors and acoustic variability.
  arXiv  Detail & Related papers  (2025-09-24T17:08:12Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• REFINER: Reasoning Feedback on Intermediate Representations [47.36251998678097]
  We introduce REFINER, a framework for finetuning language models to generate intermediate inferences. REFINER works by interacting with a critic model that provides automated feedback on the reasoning. Empirical evaluations show significant improvements over baseline LMs of comparable scale.
  arXiv  Detail & Related papers  (2023-04-04T15:57:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.