Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.06843 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908670043881472 |
|---|---|
| author | Lopez-Cardona, Angela Idesis, Sebastian Arapakis, Ioannis |
| author_facet | Lopez-Cardona, Angela Idesis, Sebastian Arapakis, Ioannis |
| contents | Recently, the integration of cognitive neuroscience in Natural Language Processing (NLP) has gained significant attention. This article provides a critical and timely overview of recent advancements in leveraging cognitive signals, particularly Eye-tracking (ET) signals, to enhance Language Models (LMs) and Multimodal Large Language Models (MLLMs). By incorporating user-centric cognitive signals, these approaches address key challenges, including data scarcity and the environmental costs of training large-scale models. Cognitive signals enable efficient data augmentation, faster convergence, and improved human alignment. The review emphasises the potential of ET data in tasks like Visual Question Answering (VQA) and mitigating hallucinations in MLLMs, and concludes by discussing emerging challenges and research trends. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06843 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating Cognitive Processing Signals into Language Models: A Review of Advances, Applications and Future Directions Lopez-Cardona, Angela Idesis, Sebastian Arapakis, Ioannis Computation and Language Artificial Intelligence Recently, the integration of cognitive neuroscience in Natural Language Processing (NLP) has gained significant attention. This article provides a critical and timely overview of recent advancements in leveraging cognitive signals, particularly Eye-tracking (ET) signals, to enhance Language Models (LMs) and Multimodal Large Language Models (MLLMs). By incorporating user-centric cognitive signals, these approaches address key challenges, including data scarcity and the environmental costs of training large-scale models. Cognitive signals enable efficient data augmentation, faster convergence, and improved human alignment. The review emphasises the potential of ET data in tasks like Visual Question Answering (VQA) and mitigating hallucinations in MLLMs, and concludes by discussing emerging challenges and research trends. |
| title | Integrating Cognitive Processing Signals into Language Models: A Review of Advances, Applications and Future Directions |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.06843 |