The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis
IntroductionThe increasing integration of large language models (LLMs) into human-AI collaboration necessitates a deeper understanding of their cognitive impacts on users. Traditional evaluation methods have primarily focused on task performance, overlooking the underlying neural dynamics during int...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2025.1556483/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849424056830394368 |
|---|---|
| author | Ting Jiang Jihua Wu Stephen C. H. Leung |
| author_facet | Ting Jiang Jihua Wu Stephen C. H. Leung |
| author_sort | Ting Jiang |
| collection | DOAJ |
| description | IntroductionThe increasing integration of large language models (LLMs) into human-AI collaboration necessitates a deeper understanding of their cognitive impacts on users. Traditional evaluation methods have primarily focused on task performance, overlooking the underlying neural dynamics during interaction.MethodsIn this study, we introduce a novel framework that leverages electroencephalography (EEG) signals to assess how LLM interactions affect cognitive processes such as attention, cognitive load, and decision-making. Our framework integrates an Interaction-Aware Language Transformer (IALT), which enhances token-level modeling through dynamic attention mechanisms, and an Interaction-Optimized Reasoning Strategy (IORS), which employs reinforcement learning to refine reasoning paths in a cognitively aligned manner.ResultsBy coupling these innovations with real-time neural data, the framework provides a fine-grained, interpretable assessment of LLM-induced cognitive changes. Extensive experiments on four benchmark EEG datasets Database for Emotion Analysis using Physiological Signals (DEAP), A Dataset for Affect, Personality and Mood Research on Individuals and Groups (AMIGOS), SJTU Emotion EEG Dataset (SEED), and Database for Emotion Recognition through EEG and ECG Signals (DREAMER) demonstrate that our method outperforms existing models in both emotion classification accuracy and alignment with cognitive signals. The architecture maintains high performance across varied EEG configurations, including low-density, noise-prone portable systems, highlighting its robustness and practical applicability.DiscussionThese findings offer actionable insights for designing more adaptive and cognitively aware LLM systems, and open new avenues for research at the intersection of artificial intelligence and neuroscience. |
| format | Article |
| id | doaj-art-bc040111c96e44e190d993eaed6e2311 |
| institution | Kabale University |
| issn | 1662-5188 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj-art-bc040111c96e44e190d993eaed6e23112025-08-20T03:30:23ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882025-07-011910.3389/fncom.2025.15564831556483The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysisTing Jiang0Jihua Wu1Stephen C. H. Leung2Pediatric Neurological Department, Anhui Children's Hospital, Hefei, Anhui, ChinaPediatric Neurological Department, Anhui Children's Hospital, Hefei, Anhui, ChinaDepartment of Engineering, The University of Hong Kong, Hong Kong, ChinaIntroductionThe increasing integration of large language models (LLMs) into human-AI collaboration necessitates a deeper understanding of their cognitive impacts on users. Traditional evaluation methods have primarily focused on task performance, overlooking the underlying neural dynamics during interaction.MethodsIn this study, we introduce a novel framework that leverages electroencephalography (EEG) signals to assess how LLM interactions affect cognitive processes such as attention, cognitive load, and decision-making. Our framework integrates an Interaction-Aware Language Transformer (IALT), which enhances token-level modeling through dynamic attention mechanisms, and an Interaction-Optimized Reasoning Strategy (IORS), which employs reinforcement learning to refine reasoning paths in a cognitively aligned manner.ResultsBy coupling these innovations with real-time neural data, the framework provides a fine-grained, interpretable assessment of LLM-induced cognitive changes. Extensive experiments on four benchmark EEG datasets Database for Emotion Analysis using Physiological Signals (DEAP), A Dataset for Affect, Personality and Mood Research on Individuals and Groups (AMIGOS), SJTU Emotion EEG Dataset (SEED), and Database for Emotion Recognition through EEG and ECG Signals (DREAMER) demonstrate that our method outperforms existing models in both emotion classification accuracy and alignment with cognitive signals. The architecture maintains high performance across varied EEG configurations, including low-density, noise-prone portable systems, highlighting its robustness and practical applicability.DiscussionThese findings offer actionable insights for designing more adaptive and cognitively aware LLM systems, and open new avenues for research at the intersection of artificial intelligence and neuroscience.https://www.frontiersin.org/articles/10.3389/fncom.2025.1556483/fullEEG analysislarge language modelscognitive dynamicsdecision-makinghuman-AI collaboration |
| spellingShingle | Ting Jiang Jihua Wu Stephen C. H. Leung The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis Frontiers in Computational Neuroscience EEG analysis large language models cognitive dynamics decision-making human-AI collaboration |
| title | The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis |
| title_full | The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis |
| title_fullStr | The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis |
| title_full_unstemmed | The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis |
| title_short | The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis |
| title_sort | cognitive impacts of large language model interactions on problem solving and decision making using eeg analysis |
| topic | EEG analysis large language models cognitive dynamics decision-making human-AI collaboration |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2025.1556483/full |
| work_keys_str_mv | AT tingjiang thecognitiveimpactsoflargelanguagemodelinteractionsonproblemsolvinganddecisionmakingusingeeganalysis AT jihuawu thecognitiveimpactsoflargelanguagemodelinteractionsonproblemsolvinganddecisionmakingusingeeganalysis AT stephenchleung thecognitiveimpactsoflargelanguagemodelinteractionsonproblemsolvinganddecisionmakingusingeeganalysis AT tingjiang cognitiveimpactsoflargelanguagemodelinteractionsonproblemsolvinganddecisionmakingusingeeganalysis AT jihuawu cognitiveimpactsoflargelanguagemodelinteractionsonproblemsolvinganddecisionmakingusingeeganalysis AT stephenchleung cognitiveimpactsoflargelanguagemodelinteractionsonproblemsolvinganddecisionmakingusingeeganalysis |