DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Sukmin | ko |
dc.contributor.author | Jeong, Soyeong | ko |
dc.contributor.author | Seo, Jeongyeon | ko |
dc.contributor.author | Park, Jong-Cheol | ko |
dc.date.accessioned | 2023-11-14T10:03:25Z | - |
dc.date.available | 2023-11-14T10:03:25Z | - |
dc.date.created | 2023-11-13 | - |
dc.date.issued | 2023-07-10 | - |
dc.identifier.citation | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023, pp.960 - 971 | - |
dc.identifier.uri | http://hdl.handle.net/10203/314659 | - |
dc.description.abstract | Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (PLM), the large-scale language model (LLM) is utilized as a zero-shot re-ranker with excellent results. While LLM is highly dependent on the prompts, the impact and the optimization of the prompts for the zero-shot re-ranker are not explored yet. Along with highlighting the impact of optimization on the zero-shot re-ranker, we propose a novel discrete prompt optimization method, Constrained Prompt generation (Co-Prompt), with the metric estimating the optimum for re-ranking. Co-Prompt guides the generated texts from PLM toward optimal prompts based on the metric without parameter update. The experimental results demonstrate that Co-Prompt leads to outstanding re-ranking performance against the baselines. Also, Co-Prompt generates more interpretable prompts for humans against other prompt optimization methods. | - |
dc.language | English | - |
dc.publisher | Association for Computational Linguistics (ACL) | - |
dc.title | Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85175229467 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 960 | - |
dc.citation.endingpage | 971 | - |
dc.citation.publicationname | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Toronto | - |
dc.contributor.localauthor | Park, Jong-Cheol | - |
dc.contributor.nonIdAuthor | Seo, Jeongyeon | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.