Can Large Language Models Understand Context?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910314711220224 |
|---|---|
| author | Zhu, Yilun Moniz, Joel Ruben Antony Bhargava, Shruti Lu, Jiarui Piraviperumal, Dhivya Li, Site Zhang, Yuan Yu, Hong Tseng, Bo-Hsiang |
| author_facet | Zhu, Yilun Moniz, Joel Ruben Antony Bhargava, Shruti Lu, Jiarui Piraviperumal, Dhivya Li, Site Zhang, Yuan Yu, Hong Tseng, Bo-Hsiang |
| contents | Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various domains within the realm of Natural Language Processing, limited attention has been paid to probing their linguistic capability of understanding contextual features. This paper introduces a context understanding benchmark by adapting existing datasets to suit the evaluation of generative models. This benchmark comprises of four distinct tasks and nine datasets, all featuring prompts designed to assess the models' ability to understand context. First, we evaluate the performance of LLMs under the in-context learning pretraining scenario. Experimental results indicate that pre-trained dense models struggle with understanding more nuanced contextual features when compared to state-of-the-art fine-tuned models. Second, as LLM compression holds growing significance in both research and real-world applications, we assess the context understanding of quantized models under in-context-learning settings. We find that 3-bit post-training quantization leads to varying degrees of performance reduction on our benchmark. We conduct an extensive analysis of these scenarios to substantiate our experimental results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00858 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can Large Language Models Understand Context? Zhu, Yilun Moniz, Joel Ruben Antony Bhargava, Shruti Lu, Jiarui Piraviperumal, Dhivya Li, Site Zhang, Yuan Yu, Hong Tseng, Bo-Hsiang Computation and Language Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various domains within the realm of Natural Language Processing, limited attention has been paid to probing their linguistic capability of understanding contextual features. This paper introduces a context understanding benchmark by adapting existing datasets to suit the evaluation of generative models. This benchmark comprises of four distinct tasks and nine datasets, all featuring prompts designed to assess the models' ability to understand context. First, we evaluate the performance of LLMs under the in-context learning pretraining scenario. Experimental results indicate that pre-trained dense models struggle with understanding more nuanced contextual features when compared to state-of-the-art fine-tuned models. Second, as LLM compression holds growing significance in both research and real-world applications, we assess the context understanding of quantized models under in-context-learning settings. We find that 3-bit post-training quantization leads to varying degrees of performance reduction on our benchmark. We conduct an extensive analysis of these scenarios to substantiate our experimental results. |
| title | Can Large Language Models Understand Context? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.00858 |