DateLogicQA: Benchmarking Temporal Biases in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915292243820544 |
|---|---|
| author | Bhatia, Gagan Tang, MingZe Mahanta, Cristina Kazi, Madiha |
| author_facet | Bhatia, Gagan Tang, MingZe Mahanta, Cristina Kazi, Madiha |
| contents | This paper introduces DateLogicQA, a benchmark with 190 questions covering diverse date formats, temporal contexts, and reasoning types. We propose the Semantic Integrity Metric to assess tokenization quality and analyse two biases: Representation-Level Bias, affecting embeddings, and Logical-Level Bias, influencing reasoning outputs. Our findings provide a comprehensive evaluation of LLMs' capabilities and limitations in temporal reasoning, highlighting key challenges in handling temporal data accurately. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13377 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DateLogicQA: Benchmarking Temporal Biases in Large Language Models Bhatia, Gagan Tang, MingZe Mahanta, Cristina Kazi, Madiha Computation and Language Artificial Intelligence This paper introduces DateLogicQA, a benchmark with 190 questions covering diverse date formats, temporal contexts, and reasoning types. We propose the Semantic Integrity Metric to assess tokenization quality and analyse two biases: Representation-Level Bias, affecting embeddings, and Logical-Level Bias, influencing reasoning outputs. Our findings provide a comprehensive evaluation of LLMs' capabilities and limitations in temporal reasoning, highlighting key challenges in handling temporal data accurately. |
| title | DateLogicQA: Benchmarking Temporal Biases in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.13377 |