Saama Technologies at SemEval-2024 Task 2: Three-module System for NLI4CT Enhanced by LLM-generated Intermediate Labels

Hwanmun Kim, Kamal Raj Kanakarajan, Malaikannan Sankarasubbu


Abstract
Participating in SemEval 2024 Task 2, we built a three-module system to predict entailment labels for NLI4CT, which consists of a sequence of the query generation module, the query answering module, and the aggregation module. We fine-tuned or prompted each module with the intermediate labels we generated with LLMs, and we optimized the combinations of different modules through experiments. Our system is ranked 19th ~ 24th in the SemEval 2024 Task 2 leaderboard in different metrics. We made several interesting observations regarding the correlation between different metrics and the sensitivity of our system on the aggregation module. We performed the error analysis on our system which can potentially help to improve our system further.
Anthology ID:
2024.semeval-1.205
Volume:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1435–1435
Language:
URL:
https://aclanthology.org/2024.semeval-1.205
DOI:
Bibkey:
Cite (ACL):
Hwanmun Kim, Kamal Raj Kanakarajan, and Malaikannan Sankarasubbu. 2024. Saama Technologies at SemEval-2024 Task 2: Three-module System for NLI4CT Enhanced by LLM-generated Intermediate Labels. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1435–1435, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Saama Technologies at SemEval-2024 Task 2: Three-module System for NLI4CT Enhanced by LLM-generated Intermediate Labels (Kim et al., SemEval 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.semeval-1.205.pdf
Supplementary material:
 2024.semeval-1.205.SupplementaryMaterial.txt