TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913376381173760 |
|---|---|
| author | Khatun, Aisha Brown, Daniel G. |
| author_facet | Khatun, Aisha Brown, Daniel G. |
| contents | Large Language Model (LLM) evaluation is currently one of the most important areas of research, with existing benchmarks proving to be insufficient and not completely representative of LLMs' various capabilities. We present a curated collection of challenging statements on sensitive topics for LLM benchmarking called TruthEval. These statements were curated by hand and contain known truth values. The categories were chosen to distinguish LLMs' abilities from their stochastic nature. We perform some initial analyses using this dataset and find several instances of LLMs failing in simple tasks showing their inability to understand simple questions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01855 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability Khatun, Aisha Brown, Daniel G. Computation and Language Artificial Intelligence Large Language Model (LLM) evaluation is currently one of the most important areas of research, with existing benchmarks proving to be insufficient and not completely representative of LLMs' various capabilities. We present a curated collection of challenging statements on sensitive topics for LLM benchmarking called TruthEval. These statements were curated by hand and contain known truth values. The categories were chosen to distinguish LLMs' abilities from their stochastic nature. We perform some initial analyses using this dataset and find several instances of LLMs failing in simple tasks showing their inability to understand simple questions. |
| title | TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.01855 |