ANALOGICAL - A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models

Thilini Wijesiriwardene, Ruwan Wickramarachchi, Bimal Gajera, Shreeyash Gowaikar, Chandan Gupta, Aman Chadha, Aishwarya Naresh Reganti, Amit Sheth, Amitava Das


Abstract
Over the past decade, analogies, in the form of word-level analogies, have played a significant role as an intrinsic measure of evaluating the quality of word embedding methods such as word2vec. Modern large language models (LLMs), however, are primarily evaluated on extrinsic measures based on benchmarks such as GLUE and SuperGLUE, and there are only a few investigations on whether LLMs can draw analogies between long texts. In this paper, we present ANALOGICAL, a new benchmark to intrinsically evaluate LLMs across a taxonomy of analogies of long text with six levels of complexity – (i) word, (ii) word vs. sentence, (iii) syntactic, (iv) negation, (v) entailment, and (vi) metaphor. Using thirteen datasets and three different distance measures, we evaluate the abilities of eight LLMs in identifying analogical pairs in the semantic vector space. Our evaluation finds that it is increasingly challenging for LLMs to identify analogies when going up the analogy taxonomy.
Anthology ID:
2023.findings-acl.218
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3534–3549
Language:
URL:
https://aclanthology.org/2023.findings-acl.218
DOI:
10.18653/v1/2023.findings-acl.218
Bibkey:
Cite (ACL):
Thilini Wijesiriwardene, Ruwan Wickramarachchi, Bimal Gajera, Shreeyash Gowaikar, Chandan Gupta, Aman Chadha, Aishwarya Naresh Reganti, Amit Sheth, and Amitava Das. 2023. ANALOGICAL - A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3534–3549, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
ANALOGICAL - A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models (Wijesiriwardene et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.218.pdf