Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2311.17438 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917687226007552 |
|---|---|
| author | Huang, Yinya Hong, Ruixin Zhang, Hongming Shao, Wei Yang, Zhicheng Yu, Dong Zhang, Changshui Liang, Xiaodan Song, Linqi |
| author_facet | Huang, Yinya Hong, Ruixin Zhang, Hongming Shao, Wei Yang, Zhicheng Yu, Dong Zhang, Changshui Liang, Xiaodan Song, Linqi |
| contents | In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought processes within LLMs and rigorously assess these processes for their validity. Specifically, we introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. To effectively evaluate a generation model's counterfactual capabilities, we propose an innovative evaluation metric, the decomposed Self-Evaluation Score (SES) to directly evaluate the natural language output of LLMs instead of modeling the task as a multiple-choice problem. Analysis shows that the proposed automatic metric aligns well with human preference. Our experimental results show that while LLMs demonstrate a notable capacity for logical counterfactual thinking, there remains a discernible gap between their current abilities and human performance. Code and data are available at https://github.com/Eleanor-H/CLOMO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_17438 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | CLOMO: Counterfactual Logical Modification with Large Language Models Huang, Yinya Hong, Ruixin Zhang, Hongming Shao, Wei Yang, Zhicheng Yu, Dong Zhang, Changshui Liang, Xiaodan Song, Linqi Computation and Language Artificial Intelligence In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought processes within LLMs and rigorously assess these processes for their validity. Specifically, we introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. To effectively evaluate a generation model's counterfactual capabilities, we propose an innovative evaluation metric, the decomposed Self-Evaluation Score (SES) to directly evaluate the natural language output of LLMs instead of modeling the task as a multiple-choice problem. Analysis shows that the proposed automatic metric aligns well with human preference. Our experimental results show that while LLMs demonstrate a notable capacity for logical counterfactual thinking, there remains a discernible gap between their current abilities and human performance. Code and data are available at https://github.com/Eleanor-H/CLOMO. |
| title | CLOMO: Counterfactual Logical Modification with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2311.17438 |