SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection

• URL: http://arxiv.org/abs/2604.26375v1
• Date: Wed, 29 Apr 2026 07:37:03 GMT
• Title: SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection
• Abstract summary: Our system classifies English political interview responses by coarse-grained clarity (3-way) and fine-grained evasion strategy (9-way)<n>A shared RoBERTa-large encoder supplies two task-specific heads trained jointly via a multi-task objective.<n>Our system achieves a Macro-F1 of 0.80 on Subtask 1 and 0.51 on Subtask 2, ranking 11th in both subtasks.
• Score: 0.6445605125467574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We describe our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which classifies English political interview responses by coarse-grained clarity (3-way) and fine-grained evasion strategy (9-way). Since responses frequently exceed the 512-token limit of standard Transformer encoders, we apply an overlapping sliding-window chunking strategy with element-wise Max-Pooling aggregation over chunk representations. A shared RoBERTa-large encoder supplies two task-specific heads trained jointly via a multi-task objective, with inference-time ensembling over 7-fold stratified cross-validation. Our system achieves a Macro-F1 of 0.80 on Subtask 1 and 0.51 on Subtask 2, ranking 11th in both subtasks.

Related papers

• pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning [5.0147105079462415]
  Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs)<n>In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Reuse Extension Task (Task B)<n>Our system employs Qwen2.5-14B-Instruct with all-MiniLM-L6-v2 for demonstration retrieval, selecting the top-5 examples for Task A and top-2 for Task B.<n>For Task B, generated triples undergo deterministic vocabulary-constrained filtering, retaining triples when at least one endpoint belongs to the sample's
  arXiv  Detail & Related papers  (2026-08-27T13:16:55Z)
• UCSC NLP at SemEval-2026 Task 10: Boundary-Aware Span Extraction and RoBERTa Classification for Conspiracy Detection [0.06808132439548074]
  We formulate the task as multi-label span classification over enumerated candidate spans, using IoU >= 0.95 positive labeling, hard-negative sampling, and containment-based non-maximum suppression (NMS)<n>For marker extraction, we formulate the task as multi-label span classification over enumerated candidate spans, using IoU >= 0.95 positive labeling, hard-negative sampling, and containment-based non-maximum suppression (NMS) with boundary-aware span representations.<n>Analysis shows that entity-like roles (Actor, Victim) are detected robustly, while abstract roles (Action, Effect, Evidence)
  arXiv  Detail & Related papers  (2026-07-06T23:15:52Z)
• ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection [0.006227637802384129]
  This paper describes our system for SemEval-2026 Task 6, which addresses the classification of political evasion strategies in English question-answer pairs extracted from U.S. presidential interviews.
  arXiv  Detail & Related papers  (2026-06-14T12:09:23Z)
• Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG [2.9721401411878254]
  Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits.<n>We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking.
  arXiv  Detail & Related papers  (2026-06-05T07:28:01Z)
• Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026 [57.48615919717867]
  We present KIT's submission to the Long and Short Instruction Following tracks in the unconstrained setting.<n>Our approach combines a general data augmentation pipeline that converts short-form corpora into long-form training data.<n>We show that likelihood-based re-ranking, while highly effective for ASR, systematically degrades semantic tasks.
  arXiv  Detail & Related papers  (2026-06-03T11:13:37Z)
• Multi-Task Optimization over Networks of Tasks [1.7499351967216341]
  We introduce MONET, a multi-task optimization algorithm that models the task space as a graph.<n>Social learning generates candidates from neighboring nodes via crossover, with individual learning, which refines a node's own solution independently via mutation.<n>We show that MONET matches or exceeds the performance of existing MAP-Elites-based baselines across all four domains.
  arXiv  Detail & Related papers  (2026-04-23T18:18:20Z)
• Duluth at SemEval-2026 Task 6: DeBERTa with LLM-Augmented Data for Unmasking Political Question Evasions [0.0]
  We address Task 1 (clarity-level classification) and Task 2 (evasion-level classification)<n>Our system is based on DeBERTa-V3-base, extended with focal loss, layer-wise learning rate decay, and Duluth discourse features.<n>To address class imbalance in the training data, we augment minority classes using synthetic examples generated by Gemini 3 and Claude Sonnet 4.5.
  arXiv  Detail & Related papers  (2026-04-22T04:18:14Z)
• MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction [50.992213877904305]
  MTLSI-Net captures comprehensive cross-task interactions at linear complexity with reduced parameters.<n>Experiments on NYUDv2 and PASCAL-Context demonstrate that MTLSI-Net achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-02T13:02:48Z)
• AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations [14.20669481486209]
  We present the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval)<n>We address all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-to-end RAG (C)<n>Our unified architecture is built on two principles: (i) a query-diversity-over-retriever-diversity strategy, and (ii) a multistage generation pipeline.
  arXiv  Detail & Related papers  (2026-03-11T08:28:31Z)
• MM-ACT: Learn from Multimodal Parallel Generation to Act [80.9182259389658]
  MM-ACT integrates text, image, and action in shared token space and performs generation across all three modalities.<n> Context-Shared Multimodal Learning supervises generation in all three modalities from a shared context.<n>Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0.
  arXiv  Detail & Related papers  (2025-11-30T16:46:35Z)
• AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents [60.881609323604685]
  Agent Synth is a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets.<n>Our pipeline achieves a low average cost of $0.60 per trajectory, orders of magnitude cheaper than human annotations.
  arXiv  Detail & Related papers  (2025-06-17T05:46:52Z)
• Localizing Task Information for Improved Model Merging and Compression [61.16012721460561]
  We show that the information required to solve each task is still preserved after merging as different tasks mostly use non-overlapping sets of weights. We propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches.
  arXiv  Detail & Related papers  (2024-05-13T14:54:37Z)
• Task Indicating Transformer for Task-conditional Dense Predictions [16.92067246179703]
  We introduce a novel task-conditional framework called Task Indicating Transformer (TIT) to tackle this challenge. Our approach designs a Mix Task Adapter module within the transformer block, which incorporates a Task Indicating Matrix through matrix decomposition. We also propose a Task Gate Decoder module that harnesses a Task Indicating Vector and gating mechanism to facilitate adaptive multi-scale feature refinement.
  arXiv  Detail & Related papers  (2024-03-01T07:06:57Z)
• Robust Subtask Learning for Compositional Generalization [20.54144051436337]
  We focus on the problem of training subtask policies in a way that they can be used to perform any task. We aim to maximize the worst-case performance over all tasks as opposed to the average-case performance.
  arXiv  Detail & Related papers  (2023-02-06T18:19:25Z)
• Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations [63.04466647849211]
  Methods typically encode task information with a simple dataset name as a prefix to the encoder. We propose compositional task configurations, a set of prompts prepended to the encoder to improve cross-task generalization. We show this not only allows the model to better learn shared knowledge across different tasks at training, but also allows us to control the model by composing new configurations.
  arXiv  Detail & Related papers  (2022-12-17T02:20:14Z)

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.