From Two Passes to One: Compact and Efficient Target-Stance Extraction

• URL: http://arxiv.org/abs/2609.06108v1
• Date: Sat, 05 Sep 2026 14:07:43 GMT
• Title: From Two Passes to One: Compact and Efficient Target-Stance Extraction
• Abstract summary: We present a one-pass, joint architecture that predicts both in a single forward pass.<n>Standard target-scrubbing practices artificially suppress target prediction accuracy.<n> Retaining explicit target mentions improves F1 by at least 6 points across both target classification and target generation settings.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Target-Stance Extraction (TSE) is the task of predicting both the target (or topic) of an author's writing and the author's stance toward it. Existing approaches to TSE use a sequential pipeline of two separate neural models: one to identify the target and another to determine the stance. We present a one-pass, joint architecture that predicts both in a single forward pass, reducing trainable parameters by nearly 50% with only a 4-7 F1 point tradeoff in performance. We further demonstrate that standard target-scrubbing practices artificially suppress target prediction accuracy. Retaining explicit target mentions, as in real-world deployments, improves F1 by at least 6 points across both target classification and target generation settings. These improvements allow for significantly easier integration of TSE in downstream applications such as public opinion tracking.

Related papers

• A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design [47.42907478044802]
  Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory.<n>Strictly fitting toward this one-hot target may be suboptimal, especially when the pretrained model encodes a rich knowledge prior.<n>In this work, we reinterpret SFT as target distribution design: instead of studying only the loss objective, we analyze the token-level target that the loss drives the model to match.
  arXiv  Detail & Related papers  (2026-06-09T17:59:54Z)
• Diagnosing Capability Gaps in Fine-Tuning Data [24.893074850115394]
  We introduce GoalCover, a framework that helps practitioners detect capability gaps in fine-tuning datasets.<n>GoalCover guides a practitioner through structured decomposition of a high-level goal into atomic, independently evaluable subgoals.<n>We show that GoalCover reliably distinguishes targeted from non-targeted capability impacts.
  arXiv  Detail & Related papers  (2026-04-30T07:52:28Z)
• TALENT: Target-aware Efficient Tuning for Referring Image Segmentation [42.766432845564786]
  Referring image segmentation aims to segment specific targets based on a natural text expression.<n>Existing PET-based methods often suffer from the fact that visual features can't emphasize the text-referred target instance.<n>We propose a novel framework, TALENT, which utilizes target-aware efficient tuning for PET-based RIS.
  arXiv  Detail & Related papers  (2026-04-01T08:13:33Z)
• Zero-Shot Stance Detection in the Wild: Dynamic Target Generation and Multi-Target Adaptation [13.424443287821118]
  We propose a novel task: zero-shot stance detection in the wild with Dynamic Target Generation and Multi-Target Adaptation.<n>We construct a Chinese social media stance detection dataset and design multi-dimensional evaluation metrics.
  arXiv  Detail & Related papers  (2026-01-27T17:04:18Z)
• Stanceformer: Target-Aware Transformer for Stance Detection [59.69858080492586]
  Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively. We introduce Stanceformer, a target-aware transformer model that incorporates enhanced attention towards the targets during both training and inference.
  arXiv  Detail & Related papers  (2024-10-09T17:24:28Z)
• Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation [210.46684938698485]
  We study unsupervised domain adaptation (UDA) for semantic segmentation. We find that, by decreasing/increasing the proportion of training samples from the target domain, the 'learning ability' is strengthened/weakened. We propose a novel dual teacher-student (DTS) framework and equip it with a bidirectional learning strategy.
  arXiv  Detail & Related papers  (2023-03-16T05:04:10Z)
• Learning What Not to Segment: A New Perspective on Few-Shot Segmentation [63.910211095033596]
  Recently few-shot segmentation (FSS) has been extensively developed. This paper proposes a fresh and straightforward insight to alleviate the problem. In light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting.
  arXiv  Detail & Related papers  (2022-03-15T03:08:27Z)
• Generative multitask learning mitigates target-causing confounding [61.21582323566118]
  We propose a simple and scalable approach to causal representation learning for multitask learning. The improvement comes from mitigating unobserved confounders that cause the targets, but not the input. Our results on the Attributes of People and Taskonomy datasets reflect the conceptual improvement in robustness to prior probability shift.
  arXiv  Detail & Related papers  (2022-02-08T20:42:14Z)
• Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation [14.050836886292869]
  We introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. We verify the effectiveness of such methods in the autonomous driving setting.
  arXiv  Detail & Related papers  (2021-04-06T16:07:22Z)
• Two-phase Pseudo Label Densification for Self-training based Domain Adaptation [93.03265290594278]
  We propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD. In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images. In the second phase, we perform a confidence-based easy-hard classification. To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss.
  arXiv  Detail & Related papers  (2020-12-09T02:35:25Z)

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.