Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915182349910016 |
|---|---|
| author | He, Zicong Zhang, Boxuan Cheng, Lu |
| author_facet | He, Zicong Zhang, Boxuan Cheng, Lu |
| contents | Large language models (LLMs) are known to hallucinate, a phenomenon often linked to creativity. While previous research has primarily explored this connection through theoretical or qualitative lenses, our work takes a quantitative approach to systematically examine the relationship between hallucination and creativity in LLMs. Given the complex nature of creativity, we propose a narrow definition tailored to LLMs and introduce an evaluation framework, HCL, which quantifies Hallucination and Creativity across different Layers of LLMs during decoding. Our empirical analysis reveals a tradeoff between hallucination and creativity that is consistent across layer depth, model type, and model size. Notably, across different model architectures, we identify a specific layer at each model size that optimally balances this tradeoff. Additionally, the optimal layer tends to appear in the early layers of larger models, and the confidence of the model is also significantly higher at this layer. These findings provide a quantitative perspective that offers new insights into the interplay between LLM creativity and hallucination. The code and data for our experiments are available at https://github.com/ZicongHe2002/HCL-Spark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02851 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers He, Zicong Zhang, Boxuan Cheng, Lu Computation and Language Large language models (LLMs) are known to hallucinate, a phenomenon often linked to creativity. While previous research has primarily explored this connection through theoretical or qualitative lenses, our work takes a quantitative approach to systematically examine the relationship between hallucination and creativity in LLMs. Given the complex nature of creativity, we propose a narrow definition tailored to LLMs and introduce an evaluation framework, HCL, which quantifies Hallucination and Creativity across different Layers of LLMs during decoding. Our empirical analysis reveals a tradeoff between hallucination and creativity that is consistent across layer depth, model type, and model size. Notably, across different model architectures, we identify a specific layer at each model size that optimally balances this tradeoff. Additionally, the optimal layer tends to appear in the early layers of larger models, and the confidence of the model is also significantly higher at this layer. These findings provide a quantitative perspective that offers new insights into the interplay between LLM creativity and hallucination. The code and data for our experiments are available at https://github.com/ZicongHe2002/HCL-Spark. |
| title | Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.02851 |