mlsanityData to 14 Oct 2026

nchellwig at SemEval-2026 Task 3: Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis using Large Language Models

arXiv 2603.01788 ↗First posted 2 Mar 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We present Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis in SemEval-2026 Task 3 (Track A). SCSG enhances prediction reliability by executing a LoRA-adapted large language model multiple times per instance, retaining only tuples that achieve a majority consensus across runs. To mitigate the computational overhead of multiple forward passes, we leverage vLLM's PagedAttention mechanism for efficient key--value cache reuse. Evaluation across 6 languages and 8 language--domain combinations demonstrates that self-consistency with 15 executions yields statistically significant improvements over single-inference prompting, with our system (leveraging Gemma 3) ranking in the top seven across all settings, achieving second place on three out of four English subsets and first place on Tatar-Restaurant for DimASTE.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 17 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

6 of 17 references.

References · 6

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2021Aspect Sentiment Quad Prediction as Paraphrase Generationcited by 100
  4. 2023MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Predictioncited by 50
  5. 2022Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentationcited by 30
  6. 2025Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Predictioncited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison
  2. 2026Dependency Reasoning for Aspect Sentiment Quadruple Prediction
  3. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
  4. 2026S2IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
  5. 2021Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
  6. 2025From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
  7. 2025An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models
  8. 2021Attribute Alignment: Controlling Text Generation from Pre-trained Language Models