Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling

• URL: http://arxiv.org/abs/2605.18007v1
• Date: Mon, 18 May 2026 08:03:02 GMT
• Title: Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
• Abstract summary: Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains.<n>We introduce RISE, an inference-time semantic reranking framework that leverages label semantics to refine predictions on hard instances.<n>Experiments on eight domain-specific RRL datasets with seven LMs, including encoder-based and causal architectures, show an average gain of +9.15 macro-F1 points on hard examples.
• Score: 5.963398606353896
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) achieve strong average performance, they remain unreliable on hard examples, where prediction confidence is low. Existing approaches typically handle uncertainty implicitly and treat labels as discrete identifiers, overlooking the semantic information encoded in label names. We introduce RISE, an inference-time semantic reranking framework that leverages label semantics to refine predictions on hard instances. RISE automatically identifies low-confidence predictions and reranks model outputs using contrastively learned label representations, without retraining or modifying the underlying model. Experiments on eight domain-specific RRL datasets with seven LMs, including encoder-based and causal architectures, show an average gain of +9.15 macro-F1 points on hard examples. For explainability, we further propose manual hardness annotations to study difficulty from both model and human perspectives, revealing a moderate agreement with Cohen's kappa = 0.40.

Related papers

• Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning [47.92504362652887]
  Semi-supervised learning faces significant challenges in realistic scenarios where labeled data is scarce and unlabeled data follows unknown, arbitrary distributions.<n>We formalize this critical yet under-explored paradigm as Universal Semi-supervised Learning (UniSSL)<n>We introduce a weighting strategy based on distribution-agnostic metrics to prioritize reliable pseudo-labels and an auxiliary branch to isolate potentially erroneous pseudo-labels.
  arXiv  Detail & Related papers  (2026-05-08T10:33:09Z)
• Optimizing LLM Annotation of Classroom Discourse through Multi-Agent Orchestration [0.21410799064827235]
  Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data.<n>However, growing evidence suggests that single-pass LLM outputs remain unreliable for high-stakes educational constructs.<n>This tension between scale and validity sits at the core of contemporary education data science.
  arXiv  Detail & Related papers  (2026-03-08T16:51:03Z)
• Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts [41.162545164426085]
  We explore label verification in contexts using Large Language Models (LLMs)<n>We propose the Label-in-a-Haystack Rectification (LiaHR) framework for subjective label correction.<n>This approach can be integrated into annotation pipelines to enhance signal-to-noise ratios.
  arXiv  Detail & Related papers  (2025-05-22T18:55:22Z)
• Uncertainty-Aware Label Refinement on Hypergraphs for Personalized Federated Facial Expression Recognition [58.98052764581606]
  We develop a novel uncertainty-Aware label refineMent on hYpergraphs (AMY) method.<n>For local training, each local model consists of a backbone, an uncertainty estimation (UE) block, and an expression classification (EC) block.<n>A personalized uncertainty estimator is then introduced to estimate reliable uncertainty weights of samples in the local client.
  arXiv  Detail & Related papers  (2025-01-03T13:59:21Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• 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)
• Ground Truth Inference for Weakly Supervised Entity Matching [76.6732856489872]
  We propose a simple but powerful labeling model for weak supervision tasks. We then tailor the labeling model specifically to the task of entity matching. We show that our labeling model results in a 9% higher F1 score on average than the best existing method.
  arXiv  Detail & Related papers  (2022-11-13T17:57:07Z)
• Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification [121.63992191386502]
  Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. We propose a semi-supervised few-shot classification method that assigns an appropriate label to each unlabeled sample by a manually defined metric. A major novelty of SALA is the task-adaptive metric, which can learn the metric adaptively for different tasks in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-06-16T13:14:03Z)
• Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation [44.319739489968164]
  Deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks. In this study, we focus on the spurious correlation between word features and labels that models learn from the biased data distribution. We propose a training strategy Less-Learn-Shortcut (LLS): our strategy quantifies the biased degree of the biased examples and down-weights them accordingly.
  arXiv  Detail & Related papers  (2022-05-25T09:08:35Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning [47.21354101796544]
  This paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.
  arXiv  Detail & Related papers  (2020-07-15T03:38:09Z)

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.