Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction

• URL: http://arxiv.org/abs/2511.23184v1
• Date: Fri, 28 Nov 2025 13:52:01 GMT
• Title: Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction
• Abstract summary: Aspect sentiment quad prediction (ASQP) is inherently challenging to predict a structured quadruple with four core sentiment elements.<n>Prior methods relying on marker-based prediction struggle with modeling the intricate relationships among elements.<n>We employ reasoning-based generation to output both the quadruple and a natural language rationale under element prefixes within a unified template.
• Score: 14.189537313152954
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Aspect sentiment quad prediction (ASQP) is inherently challenging to predict a structured quadruple with four core sentiment elements, including aspect term (a), aspect category (c), opinion term (o), and sentiment polarity (s). Prior methods relying on marker-based prediction struggle with modeling the intricate relationships among elements and experience sharp performance declines when predicting higher-order elements (e.g., c and s) under standard supervised fine-tuning. To address these limitations, we employ reasoning-based generation to output both the quadruple and a natural language rationale under element prefixes within a unified template, encouraging explicit relational reasoning and interpretability. To further enhance element-wise alignment, we introduce a listwise preference optimization framework for improving structural validity and relational coherence. Specifically, we generate element-wise confusable candidates via syntactic and semantic proximity, then train the model with listwise objectives to prefer the gold candidates over closely competing alternatives. Extensive experiments on four benchmark datasets demonstrate that our framework effectively improves quadruple prediction accuracy and explanation consistency.

Related papers

• CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging [95.02210956333374]
  We propose a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation.<n>On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy.
  arXiv  Detail & Related papers  (2026-05-19T10:59:19Z)
• Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models [102.20309135516186]
  Cross-entropy (CE) training provides dense and scalable supervision for language models.<n>We introduce a feature-matching objective for language-model fine-tuning.<n>To optimize this objective efficiently, we propose energy-based fine-tuning.
  arXiv  Detail & Related papers  (2026-03-12T17:57:50Z)
• REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation [10.151027538362259]
  REVEALER is a unified framework for element-level alignment evaluation based on reinforcement-guided visual reasoning.<n>Our method enables Multimodal Large Language Models (MLLMs) to explicitly localize semantic elements and derive interpretable alignment judgments.
  arXiv  Detail & Related papers  (2025-12-29T03:24:09Z)
• AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset [89.37514696019484]
  Preference learning is critical for aligning large language models with human values.<n>Our work shifts preference dataset design from ad hoc scaling to component-aware optimization.
  arXiv  Detail & Related papers  (2025-04-04T17:33:07Z)
• STAR: Stepwise Task Augmentation and Relation Learning for Aspect Sentiment Quad Prediction [18.836998294161834]
  Aspect-based sentiment analysis (ABSA) aims to identify four sentiment elements, including aspect term, aspect category, opinion term, and sentiment polarity.<n>The most challenging task, aspect sentiment quad prediction (ASQP), predicts these elements simultaneously, hindered by difficulties in accurately coupling different sentiment elements.<n>We propose stepwise task augmentation and relation learning (STAR), a strategy inspired by human reasoning.
  arXiv  Detail & Related papers  (2025-01-27T14:41:20Z)
• Improving Context-Aware Preference Modeling for Language Models [62.32080105403915]
  We consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We contribute context-conditioned preference datasets and experiments that investigate the ability of language models to evaluate context-specific preference.
  arXiv  Detail & Related papers  (2024-07-20T16:05:17Z)
• Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy [17.477542644785483]
  We propose Self-Consistent Reasoning-based Aspect-sentiment quadruple Prediction (SCRAP) SCRAP optimize its model to generate reasonings and the corresponding sentiment quadruplets in sequence. In the end, SCRAP significantly improves the model's ability to handle complex reasoning tasks and correctly predict quadruplets through consistency voting.
  arXiv  Detail & Related papers  (2024-03-01T08:34:02Z)
• Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency [87.16283281290053]
  Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities. We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions. We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points.
  arXiv  Detail & Related papers  (2023-11-06T16:40:13Z)
• UATVR: Uncertainty-Adaptive Text-Video Retrieval [90.8952122146241]
  A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities. We propose an Uncertainty-language Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure.
  arXiv  Detail & Related papers  (2023-01-16T08:43:17Z)
• Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation [14.962445913454747]
  aspect sentiment quad prediction (ASQP) has become a popular task in the field of aspect-level sentiment analysis. Previous work utilizes a predefined template to paraphrase the original sentence into a structure target sequence. We study the effects of template orders and find that some orders help the generative model achieve better performance.
  arXiv  Detail & Related papers  (2022-10-19T04:31:08Z)
• Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis [72.9124467710526]
  generative approaches have been proposed to extract all four elements as (one or more) quadruplets from text as a single task. We propose a unified framework for solving ABSA, and the associated sub-tasks to improve the performance in few-shot scenarios.
  arXiv  Detail & Related papers  (2022-10-12T23:38:57Z)
• Aspect Sentiment Quad Prediction as Paraphrase Generation [53.33072918744124]
  We introduce the Aspect Sentiment Quad Prediction (ASQP) task, aiming to jointly detect all sentiment elements in quads for a given opinionated sentence. We propose a novel textscParaphrase modeling paradigm to cast the ASQP task to a paraphrase generation process. On the other hand, the semantics of the sentiment elements can be fully exploited by learning to generate them in the natural language form.
  arXiv  Detail & Related papers  (2021-10-02T12:57:27Z)

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.