SRCB at SemEval-2026 Task 5 A Multi-Target Finetuning Framework for Large Language Models with Joint Regression and Text Generation
Year: 2026
Type: conference-paper
Abstract: This paper presents our winning system for SemEval-2026 Task 5 on rating the plausibility of word senses in ambiguous stories.Unlike traditional Word Sense Disambiguation, the task requires predicting continuous plausibility scores that reflect human variability rather than selecting a single correct sense.We propose a multi-target fine-tuning framework for decoder-only large language models that jointly optimizes regression module for score prediction and text generation module for that produces both interpretable explanations and the predicted score.To address inter-annotator variability, we adopt objective-level strategies to enhance robustness.Our system achieves first place, demonstrating the effectiveness of unified regressive-generative modeling for finegrained plausibility estimation.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166887546