Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2401.12078 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917572274814976 |
|---|---|
| author | Wallat, Jonas Jatowt, Adam Anand, Avishek |
| author_facet | Wallat, Jonas Jatowt, Adam Anand, Avishek |
| contents | Large language models (LLMs) have recently gained significant attention due to their unparalleled ability to perform various natural language processing tasks. These models, benefiting from their advanced natural language understanding capabilities, have demonstrated impressive zero-shot performance. However, the pre-training data utilized in LLMs is often confined to a specific corpus, resulting in inherent freshness and temporal scope limitations. Consequently, this raises concerns regarding the effectiveness of LLMs for tasks involving temporal intents. In this study, we aim to investigate the underlying limitations of general-purpose LLMs when deployed for tasks that require a temporal understanding. We pay particular attention to handling factual temporal knowledge through three popular temporal QA datasets. Specifically, we observe low performance on detailed questions about the past and, surprisingly, for rather new information. In manual and automatic testing, we find multiple temporal errors and characterize the conditions under which QA performance deteriorates. Our analysis contributes to understanding LLM limitations and offers valuable insights into developing future models that can better cater to the demands of temporally-oriented tasks. The code is available\footnote{https://github.com/jwallat/temporalblindspots}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_12078 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Temporal Blind Spots in Large Language Models Wallat, Jonas Jatowt, Adam Anand, Avishek Computation and Language Large language models (LLMs) have recently gained significant attention due to their unparalleled ability to perform various natural language processing tasks. These models, benefiting from their advanced natural language understanding capabilities, have demonstrated impressive zero-shot performance. However, the pre-training data utilized in LLMs is often confined to a specific corpus, resulting in inherent freshness and temporal scope limitations. Consequently, this raises concerns regarding the effectiveness of LLMs for tasks involving temporal intents. In this study, we aim to investigate the underlying limitations of general-purpose LLMs when deployed for tasks that require a temporal understanding. We pay particular attention to handling factual temporal knowledge through three popular temporal QA datasets. Specifically, we observe low performance on detailed questions about the past and, surprisingly, for rather new information. In manual and automatic testing, we find multiple temporal errors and characterize the conditions under which QA performance deteriorates. Our analysis contributes to understanding LLM limitations and offers valuable insights into developing future models that can better cater to the demands of temporally-oriented tasks. The code is available\footnote{https://github.com/jwallat/temporalblindspots}. |
| title | Temporal Blind Spots in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.12078 |