Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning

• URL: http://arxiv.org/abs/2511.02044v1
• Date: Mon, 03 Nov 2025 20:25:42 GMT
• Title: Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning
• Authors: Vivswan Shah, Randy Cogill, Hanwei Yue, Gopinath Chennupati, Rinat Khaziev,
• Abstract summary: We evaluate whether attaching brief explanations to each label during fine-tuning yields better models.<n>We replace human-written explanations with text that is syntactically incoherent yet vocabulary-aligned with the originals.<n>The effect persists across datasets and training seeds, indicating that gains arise less from meaning than from structure.
• Score: 2.247737938202007
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes: naturalness, comprehensiveness, and on-topic adherence, each rated on 5-point scales. Using ensemble-generated data from multiple LLMs, we fine-tune a 7B-parameter model and test across six diverse conversational datasets. Across 18 dataset, task settings, label-plus-explanation training outperforms label-only baselines. A central and unexpected result concerns random tokens. We replace human-written explanations with text that is syntactically incoherent yet vocabulary-aligned with the originals (e.g., shuffled or bag-of-words variants). Despite lacking semantics, these pseudo-explanations still improve accuracy over label-only training and often narrow much of the gap to true explanations. The effect persists across datasets and training seeds, indicating that gains arise less from meaning than from structure: the extra token budget encourages richer intermediate computation and acts as a regularizer that reduces over-confident shortcuts. Internal analyses support this view: explanation-augmented models exhibit higher activation entropy in intermediate layers alongside sharper predictive mass at the output layer, consistent with increased deliberation before decision. Overall, explanation-augmented fine-tuning, whether with genuine rationales or carefully constructed random token sequences, improves accuracy and reliability for LLM classification while clarifying how token-level scaffolding shapes computation during inference.

Related papers

• Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation [60.18907916989796]
  Large Language Models (LLMs) generate chains of thought (CoTs) before giving the final answer.<n>We propose a novel pipeline enriched with linguistically-grounded discourse segmenters to extract supporting and opposing statements for each answer option.<n>We also propose a rank-based HLV evaluation framework that prioritizes the ranking of answers over exact scores.
  arXiv  Detail & Related papers  (2025-05-29T11:47:18Z)
• Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation [0.09558392439655014]
  We assess whether pre-trained autoregressive LLMs possess consistent, expressible knowledge about thematic fit. We evaluate both closed and open state-of-the-art LLMs on several psycholinguistic datasets. Our results show that chain-of-thought reasoning is more effective on datasets with self-explanatory semantic role labels.
  arXiv  Detail & Related papers  (2024-10-19T18:25:30Z)
• Can Language Models Explain Their Own Classification Behavior? [1.8177391253202122]
  Large language models (LLMs) perform well at a myriad of tasks, but explaining the processes behind this performance is a challenge. This paper investigates whether LLMs can give faithful high-level explanations of their own internal processes. We release our dataset, ArticulateRules, which can be used to test self-explanation for LLMs trained either in-context or by finetuning.
  arXiv  Detail & Related papers  (2024-05-13T02:31:08Z)
• FRACTAL: Fine-Grained Scoring from Aggregate Text Labels [17.052047103156372]
  Large language models (LLMs) are increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and tuning LLM performance has been provided at the response level. Recent works indicate that sentence-level labels may provide more accurate and interpretable feedback for LLM optimization.
  arXiv  Detail & Related papers  (2024-04-07T05:54:28Z)
• A Fixed-Point Approach to Unified Prompt-Based Counting [51.20608895374113]
  This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for objects indicated by various prompt types, such as box, point, and text. Our model excels in prominent class-agnostic datasets and exhibits superior performance in cross-dataset adaptation tasks.
  arXiv  Detail & Related papers  (2024-03-15T12:05:44Z)
• Explore Spurious Correlations at the Concept Level in Language Models for Text Classification [28.832684088975622]
  Language models (LMs) have achieved notable success in numerous NLP tasks. They face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations.
  arXiv  Detail & Related papers  (2023-11-15T01:58:54Z)
• Using Natural Language Explanations to Rescale Human Judgments [81.66697572357477]
  We propose a method to rescale ordinal annotations and explanations using large language models (LLMs)<n>We feed annotators' Likert ratings and corresponding explanations into an LLM and prompt it to produce a numeric score anchored in a scoring rubric.<n>Our method rescales the raw judgments without impacting agreement and brings the scores closer to human judgments grounded in the same scoring rubric.
  arXiv  Detail & Related papers  (2023-05-24T06:19:14Z)
• M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios [58.617025733655005]
  We propose a vision-language prompt tuning method with mitigated label bias (M-Tuning)<n>It introduces open words from the WordNet to extend the range of words forming the prompt texts from only closed-set label words to more, and thus prompts are tuned in a simulated open-set scenario.<n>Our method achieves the best performance on datasets with various scales, and extensive ablation studies also validate its effectiveness.
  arXiv  Detail & Related papers  (2023-03-09T09:05:47Z)
• Revisiting Self-Training for Few-Shot Learning of Language Model [61.173976954360334]
  Unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
  arXiv  Detail & Related papers  (2021-10-04T08:51:36Z)
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance [83.53855889592734]
  We introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimize the minimum Levenshtein distance (MLD) through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-30T08:44:19Z)
• Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals [72.00815192668193]
  Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
  arXiv  Detail & Related papers  (2021-06-01T20:36:48Z)

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.