Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

• URL: http://arxiv.org/abs/2606.08940v1
• Date: Mon, 08 Jun 2026 02:36:05 GMT
• Title: Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance
• Abstract summary: We study sentiment drift, a systematic shift toward neutral sentiment in RLHF-based summarization outputs compared to source texts.<n>Our results show that sentiment drift is a consistent phenomenon that becomes stronger with increased KL regularization strength.<n>We propose a sentiment-aware modification of the KL regularization term, which selectively reduces constraints on sentiment-bearing tokens.
• Score: 46.49327788332846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) has significantly improved the quality and fluency of large language models in text summarization. However, its impact on affective properties remains insufficiently understood. In this work, we study sentiment drift, a systematic shift toward neutral sentiment in RLHF-based summarization outputs compared to source texts. We conduct extensive experiments across multiple datasets, model architectures, and eight languages to analyze how alignment objectives influence sentiment preservation. Our results show that sentiment drift is a consistent phenomenon that becomes stronger with increased KL regularization strength, indicating a trade-off between alignment stability and affective fidelity. To explain this behavior, we introduce a Policy Attribution framework that decomposes the RLHF objective and quantifies the contribution of its components. Our analysis reveals that KL regularization is the primary driver of sentiment suppression across all settings. Based on these findings, we propose a sentiment-aware modification of the KL regularization term, which selectively reduces constraints on sentiment-bearing tokens. Empirical results demonstrate that this approach mitigates sentiment drift while maintaining summarization quality. Overall, our findings highlight a fundamental limitation of current alignment methods: while they improve factual consistency and safety, they may unintentionally suppress emotional expressiveness. This motivates the development of alignment strategies that explicitly account for affective preservation.

Related papers

• Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs [68.58207076756237]
  We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis.<n>We find that models faithfully perceive video content yet systematically underexploit it during causal reasoning.<n>We propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment.
  arXiv  Detail & Related papers  (2026-05-10T08:48:58Z)
• Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding [10.95036747579563]
  Vision-Language Models demonstrate remarkable capabilities but often struggle with compositional reasoning.<n>This study establishes lexical concreteness as a fundamental determinant of negative sample efficacy.<n>The integrated framework, designated as Slipform, achieves state-of-the-art accuracy across diverse compositional evaluation benchmarks.
  arXiv  Detail & Related papers  (2026-04-14T21:28:46Z)
• Identifying Influential N-grams in Confidence Calibration via Regression Analysis [53.95767806659635]
  We identify what linguistic expressions are related to confidence by applying the regression method.<n>We show that large language models (LLMs) remain overconfident when reasoning is involved.<n>We reveal that confidence calibration is possible by simply suppressing those overconfident expressions without drops in performance.
  arXiv  Detail & Related papers  (2026-04-07T11:58:49Z)
• Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction [15.348505859065689]
  We propose CISEA-MRFE, a PLM-based framework integrating Contextual Instruction (CI), Semantic Enhancement Augmentation (SEA), and Multi-Refined Feature Extraction (MRFE)<n>CISEA-MRFE consistently outperforms strong baselines, achieving relative improvements in accuracy of up to 4.6% on IMDb, 6.5% on Yelp, 30.3% on Twitter, and 4.1% on Amazon.<n>These results validate the effectiveness and generalization ability of our approach for sentiment classification across varied domains.
  arXiv  Detail & Related papers  (2025-11-01T12:46:33Z)
• Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization [33.5861323022684]
  This paper introduces a flexible synthetic testbed that combines a statistical stream of generic tokens with an abstract factual stream of source-target token pairs.<n>We find that while higher contextual diversity delays in-distribution (ID) factual accuracy, its impact on out-of-distribution (OOD) factual generalization depends critically on contextual structure.
  arXiv  Detail & Related papers  (2025-10-17T17:58:01Z)
• Enhanced Sentiment Interpretation via a Lexicon-Fuzzy-Transformer Framework [0.9558392439655014]
  We propose a novel lexicon-fuzzy-transformer framework that combines rule-baseds, contextual deep learning, and fuzzy logic.<n>The framework is rigorously evaluated on four domain-specific datasets.<n>Results show improved alignment with user ratings, better identification of sentiment extremes, and reduced misclassifications.
  arXiv  Detail & Related papers  (2025-10-17T17:36:05Z)
• Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation [57.97548022208733]
  We show that seemingly superficial choices in key-value extraction can induce shifts in accuracy and stability.<n>We introduce Contextual Normalization, a strategy that adaptively standardizes context representations before generation.
  arXiv  Detail & Related papers  (2025-10-15T06:28:25Z)
• Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection [23.153044933861988]
  We propose SentiDetect, a model-agnostic framework for detecting large language models (LLMs)-generated text.<n>Our method is motivated by the empirical observation that LLM outputs tend to exhibit emotionally consistent patterns, whereas human-written texts display greater emotional variability.<n>We evaluate SentiDetect on five diverse datasets and a range of advanced LLMs, including Gemini-1.5-Pro, Claude-3, GPT-4-0613, and LLaMa-3.3.
  arXiv  Detail & Related papers  (2025-08-09T09:55:47Z)
• Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis [56.84237932819403]
  This paper aims to estimate and mitigate the bad effect of textual modality for strong OOD generalization. Inspired by this, we devise a model-agnostic counterfactual framework for multimodal sentiment analysis.
  arXiv  Detail & Related papers  (2022-07-24T03:57:40Z)
• Balancing Robustness and Sensitivity using Feature Contrastive Learning [95.86909855412601]
  Methods that promote robustness can hurt the model's sensitivity to rare or underrepresented patterns. We propose Feature Contrastive Learning (FCL) that encourages a model to be more sensitive to the features that have higher contextual utility.
  arXiv  Detail & Related papers  (2021-05-19T20:53:02Z)

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.