Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning

• URL: http://arxiv.org/abs/2603.22619v1
• Date: Mon, 23 Mar 2026 22:43:34 GMT
• Title: Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning
• Abstract summary: We present a comprehensive analysis using FaultyScience, a newly constructed large-scale, cross-disciplinary benchmark of faulty questions.<n>We show that the gap is pervasive and stems from token-level autoregression, which entangles task selection with content generation.<n>We propose DeIllusionLLM, a task-level autoregressive framework that explicitly models this decision.
• Score: 22.264933226031435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLMs often generate seemingly valid answers to flawed or ill-posed inputs. This is not due to missing knowledge: under discriminative prompting, the same models can mostly identify such issues, yet fail to reflect this in standard generative responses. This reveals a fundamental know-act gap between discriminative recognition and generative behavior. Prior work largely characterizes this issue in narrow settings, such as math word problems or question answering, with limited focus on how to integrate these two modes. In this work, we present a comprehensive analysis using FaultyScience, a newly constructed large-scale, cross-disciplinary benchmark of faulty scientific questions. We show that the gap is pervasive and stems from token-level autoregression, which entangles task selection (validate vs. answer) with content generation, preventing discriminative knowledge from being utilized. To address this, we propose DeIllusionLLM, a task-level autoregressive framework that explicitly models this decision. Through self-distillation, the model unifies discriminative judgment and generative reasoning within a single backbone. Empirically, DeIllusionLLM substantially reduces answer-despite-error failures under natural prompting while maintaining general reasoning performance, demonstrating that self-distillation is an effective and scalable solution for bridging the discriminative-generative know-act gap

Related papers

• Negative Self-Distillation: Learning to Reason by Avoiding Flaws [17.066626113937463]
  On-Policy Self-Distillation (OPSD) has emerged as a popular paradigm for large language model (LLM) self-improvement.<n>OPSD forces the student to imitate an artificially confident reasoning trace conditioned on privileged information.<n>We introduce Negative Self-Distillation (NSD) to optimize LLMs by diverging from flawed reasoning rather than imitating privileged solutions.
  arXiv  Detail & Related papers  (2026-09-10T15:24:17Z)
• Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning [109.33717747526583]
  Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks.<n>We introduce textbfCaRL (textbfCapability-textbfaligned textbfReinforcement textbfL) to align behavior with capability boundaries.<n>Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties.
  arXiv  Detail & Related papers  (2026-07-31T09:30:33Z)
• Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning [19.177595059532557]
  We show that models become easily hijacked by useless explicit distractors, leading them to ignore the implicit physical or commonsense prerequisites of a task.<n>A critical open question is whether this failure reflects a genuine gap in commonsense knowledge or merely its suppression under misleading task framing.<n>Our findings relocate the bottleneck of commonsense reasoning failures from model competence to elicitation, and we release SaliTrap as a testbed for this blind spot.
  arXiv  Detail & Related papers  (2026-07-30T16:30:08Z)
• GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics [51.647572539626715]
  We present GRADE (Gradient Dynamics for knowledge gap detection), which quantifies the knowledge gap via the cross-layer rank ratio of the gradient to that of the corresponding hidden state subspace.<n>We validate modelname on six benchmarks, demonstrating its effectiveness and robustness to input perturbations.<n>In addition, we present a case study showing how the gradient chain can generate interpretable explanations of knowledge gaps for long-form answers.
  arXiv  Detail & Related papers  (2026-04-03T07:52:26Z)
• WakenLLM: Evaluating Reasoning Potential and Stability in LLMs via Fine-Grained Benchmarking [34.350505059394536]
  Large Language Models (LLMs) frequently output the label Unknown in reasoning tasks.<n>We introduce WakenLLM, a framework that quantifies the portion of Unknown output attributable to model incapacity.
  arXiv  Detail & Related papers  (2025-07-22T03:21:48Z)
• Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search [76.54475437069395]
  Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information.<n>We propose a dynamic distraction generation framework based on tree search, where the generation process is guided by model behavior.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation [5.255129053741665]
  Large language models (LLMs) have showcased superior capabilities in sophisticated tasks across various domains, stemming from basic question-answer (QA) This paper presents a novel way to evaluate the uncertainty that captures the directional instability, by constructing a directional graph from entailment probabilities. We also provide a way to incorporate the existing work's semantics uncertainty with our proposed layer.
  arXiv  Detail & Related papers  (2024-07-01T06:11:30Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs [58.620269228776294]
  We propose a task-agnostic framework for resolving ambiguity by asking users clarifying questions. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. We find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs.
  arXiv  Detail & Related papers  (2023-11-16T00:18:50Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)
• Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation [37.55417272177113]
  Knowledge-grounded dialogue generation aims to incorporate external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a human-like manner. We propose a Multi-level Adaptive Contrastive Learning framework that dynamically samples negative examples and subsequently penalizes degeneration behaviors.
  arXiv  Detail & Related papers  (2023-10-13T08:16:27Z)
• Disentangling Observed Causal Effects from Latent Confounders using Method of Moments [67.27068846108047]
  We provide guarantees on identifiability and learnability under mild assumptions. We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
  arXiv  Detail & Related papers  (2021-01-17T07:48:45Z)

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.