LLM-Brain Alignment Varies by Training Data and Task Specificity
ByPulseAugur Editorial·[9 sources]·
Researchers are exploring how large language models (LLMs) align with human brain activity across different languages and tasks. Studies show that intermediate LLM layers best predict brain responses, and this alignment is influenced by training data language dominance rather than inherent model typology. Furthermore, instruction-tuned multimodal LLMs demonstrate stronger brain alignment, particularly when organized around task-specific demands rather than just surface semantics.
AI
IMPACT
Investigates how LLMs process and represent information, offering insights into their cognitive alignment and potential for cross-lingual and multimodal tasks.
RANK_REASON
Multiple arXiv papers detailing novel research findings on LLM capabilities and their relationship with human cognition.
arXiv:2605.23035v1 Announce Type: cross Abstract: Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this ga…
arXiv cs.AI
TIER_1English(EN)·Dongxin Guo, Jikun Wu, Siu Ming Yiu·
arXiv:2605.23032v1 Announce Type: cross Abstract: Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test thi…
arXiv:2506.08277v3 Announce Type: replace-cross Abstract: Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain alignment compared to unimodal models. More recently, instruction-tuned multimod…
Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by bridging sparse autoencoders (SAEs) from mech…
Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test this using fMRI data from 112 participants across Eng…
Large language models (LLMs) reliably predict neural activity during language comprehension and transformer depth has been interpreted as mirroring hierarchical cortical organization. However, it remains unclear whether such alignment extends to subcortical regions, overlaps spat…
arXiv cs.CL
TIER_1English(EN)·Julius N\"aumann, Sven Keidel, Amir Molzam Sharifloo, Mira Mezini·
arXiv:2605.05282v1 Announce Type: cross Abstract: Code translation is one of the core capabilities of LLMs. However, evaluating the correctness of translations remains difficult, as commonly used metrics such as BLEU measure only syntactic similarity, disregarding program semanti…
arXiv:2604.23844v1 Announce Type: new Abstract: Cross-Lingual Text Simplification (CLTS) aims to make content more accessible across languages by simultaneously addressing both linguistic complexity and translation. This study investigates the effectiveness of different prompting…
Cross-Lingual Text Simplification (CLTS) aims to make content more accessible across languages by simultaneously addressing both linguistic complexity and translation. This study investigates the effectiveness of different prompting strategies for CLTS between English and French …
