UniBuc at SemEval-2024 Task 2: Tailored Prompting with Solar for Clinical NLI
Not on the map. Why?
Abstract (arXiv)
This paper describes the approach of the UniBuc team in tackling the SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. We used SOLAR Instruct, without any fine-tuning, while focusing on input manipulation and tailored prompting. By customizing prompts for individual CTR sections, in both zero-shot and few-shots settings, we managed to achieve a consistency score of 0.72, ranking 14th in the leaderboard. Our thorough error analysis revealed that our model has a tendency to take shortcuts and rely on simple heuristics, especially when dealing with semantic-preserving changes.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 19 references that are in the map. First posted on arXiv 30 Sep 2026.
Builds on
11 of 19 references.
References · 11
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
- 2019How to Fine-Tune BERT for Text Classification?cited by 409
- 2023SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scalingcited by 172
- 2018Lessons from Natural Language Inference in the Clinical Domaincited by 149
- 2023A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Taskscited by 36
- 2024SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trialscited by 20
- 2023NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reportscited by 18
- 2022CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Modelscited by 7
Built on by
Not cited yet.