user

Exploring Prompting Approaches in Legal Textual Entailment

被引：0
|
作者：
Onur Bilgin
Logan Fields
Antonio Laverghetta
Zaid Marji
Animesh Nighojkar
Stephen Steinle
John Licato
机构：
[1] University of South Florida,Advancing Machine and Human Reasoning Lab, Department of Computer Science and Engineering
来源：
The Review of Socionetwork Strategies | 2024年 / 18卷
关键词：
AI; NLP; Reasoning; Law; Legal;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
We report explorations into prompt engineering with large pre-trained language models that were not fine-tuned to solve the legal entailment task (Task 4) of the 2023 COLIEE competition. Our most successful strategy used simple text similarity measures to retrieve articles and queries from the training set. We report on our efforts to optimize performance with both OpenAI’s GPT-4 and FLaN-T5. We also used an ensemble approach to find the best combination of models and prompts. Finally, we analyze our results and suggest ideas for future improvements.
引用
收藏
页码：75 / 100
页数：25
相关论文
共 50 条
  • [1] Exploring Prompting Approaches in Legal Textual Entailment
    Bilgin, Onur
    Fields, Logan
    Laverghetta Jr, Antonio
    Marji, Zaid
    Nighojkar, Animesh
    Steinle, Stephen
    Licato, John
    [J]. REVIEW OF SOCIONETWORK STRATEGIES, 2024, 18 (01): : 75 - 100
  • [2] Recognizing textual entailment: Rational, evaluation and approaches
    Dagan, Ido
    Dolan, Bill
    Magnini, Bernardo
    Roth, Dan
    [J]. Natural Language Engineering, 2009, 15 (04)
  • [3] A Survey on Textual Entailment: Benchmarks, Approaches and Applications
    Alharahseheh, Yara
    Obeidat, Rasha
    Al-Ayoub, Mahmoud
    Gharaibeh, Maram
    [J]. 2022 13TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION SYSTEMS (ICICS), 2022, : 328 - 336
  • [4] Recognizing textual entailment: Rational, evaluation and approaches
    Dagan, Ido
    Dolan, Bill
    Magnini, Bernardo
    Roth, Dan
    [J]. Natural Language Engineering, 2010, 16 (01)
  • [5] Applying BERT Embeddings to Predict Legal Textual Entailment
    Wehnert, Sabine
    Dureja, Shipra
    Kutty, Libin
    Sudhi, Viju
    De Luca, Ernesto William
    [J]. REVIEW OF SOCIONETWORK STRATEGIES, 2022, 16 (01): : 197 - 219
  • [6] Applying BERT Embeddings to Predict Legal Textual Entailment
    Sabine Wehnert
    Shipra Dureja
    Libin Kutty
    Viju Sudhi
    Ernesto William De Luca
    [J]. The Review of Socionetwork Strategies, 2022, 16 : 197 - 219
  • [7] Improving abstractive summarization of legal rulings through textual entailment
    Diego de Vargas Feijo
    Viviane P. Moreira
    [J]. Artificial Intelligence and Law, 2023, 31 : 91 - 113
  • [8] Improving abstractive summarization of legal rulings through textual entailment
    Feijo, Diego de Vargas
    Moreira, Viviane P.
    [J]. ARTIFICIAL INTELLIGENCE AND LAW, 2023, 31 (01) : 91 - 113
  • [9] Recognizing textual entailment: A review of resources, approaches, applications, and challenges
    Putra, I. Made Suwija
    Siahaan, Daniel
    Saikhu, Ahmad
    [J]. ICT EXPRESS, 2024, 10 (01): : 132 - 155
  • [10] A STUDY OF TEXTUAL ENTAILMENT
    Rus, Vasile
    McCarthy, Philip M.
    McNamara, Danielle S.
    Graesser, Arthur C.
    [J]. INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2008, 17 (04) : 659 - 685
12345