{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/what-are-large-language-models-mapping-to-in","title":"What Are Large Language Models Mapping to in the Brain? A Case Against Over-Reliance on Brain Scores","arxiv_id":"2406.01538","date":"2024-06-03","proceeding":null,"authors":["Ebrahim Feghhi","Nima Hadidi","Bryan Song","Idan A. Blank","Jonathan C. Kao"],"abstract":"Given the remarkable capabilities of large language models (LLMs), there has been a growing interest in evaluating their similarity to the human brain. One approach towards quantifying this similarity is by measuring how well a model predicts neural signals, also called \"brain score\". Internal representations from LLMs achieve state-of-the-art brain scores, leading to speculation that they share computational principles with human language processing. This inference is only valid if the subset of neural activity predicted by LLMs reflects core elements of language processing. Here, we question this assumption by analyzing three neural datasets used in an impactful study on LLM-to-brain mappings, with a particular focus on an fMRI dataset where participants read short passages. We first find that when using shuffled train-test splits, as done in previous studies with these datasets, a trivial feature that encodes temporal autocorrelation not only outperforms LLMs but also accounts for the majority of neural variance that LLMs explain. We therefore use contiguous splits moving forward. Second, we explain the surprisingly high brain scores of untrained LLMs by showing they do not account for additional neural variance beyond two simple features: sentence length and sentence position. This undermines evidence used to claim that the transformer architecture biases computations to be more brain-like. Third, we find that brain scores of trained LLMs on this dataset can largely be explained by sentence length, position, and pronoun-dereferenced static word embeddings; a small, additional amount is explained by sense-specific embeddings and contextual representations of sentence structure. We conclude that over-reliance on brain scores can lead to over-interpretations of similarity between LLMs and brains, and emphasize the importance of deconstructing what LLMs are mapping to in neural signals.","url_abs":"https://arxiv.org/abs/2406.01538v2","url_pdf":"https://arxiv.org/pdf/2406.01538v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"what-are-large-language-models-mapping-to-in","repo_url":"https://github.com/ebrahimfeghhi/beyond-brainscore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"Position"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.01538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01538"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ebrahimfeghhi/beyond-brainscore","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"15d17754fadaeed5","entry":"compute_p_value","repo":"ebrahimfeghhi/beyond-brainscore","repo_kind":"official","path":"misc_code/stats_testing_funcs.py","file_url":"https://github.com/ebrahimfeghhi/beyond-brainscore/blob/HEAD/misc_code/stats_testing_funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15d17754fadaeed5"}},{"code_sha256_prefix":"cdbdae1ce67da8d6","entry":"is_punctuation","repo":"ebrahimfeghhi/beyond-brainscore","repo_kind":"official","path":"generate_activations/interp_funcs.py","file_url":"https://github.com/ebrahimfeghhi/beyond-brainscore/blob/HEAD/generate_activations/interp_funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cdbdae1ce67da8d6"}},{"code_sha256_prefix":"4e3b19fa43f47e91","entry":"is_sentence_ending_punctuation","repo":"ebrahimfeghhi/beyond-brainscore","repo_kind":"official","path":"generate_activations/interp_funcs.py","file_url":"https://github.com/ebrahimfeghhi/beyond-brainscore/blob/HEAD/generate_activations/interp_funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e3b19fa43f47e91"}},{"code_sha256_prefix":"9318f410cafebb3c","entry":"permute_matrix_in_blocks","repo":"ebrahimfeghhi/beyond-brainscore","repo_kind":"official","path":"misc_code/stats_testing_funcs.py","file_url":"https://github.com/ebrahimfeghhi/beyond-brainscore/blob/HEAD/misc_code/stats_testing_funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9318f410cafebb3c"}},{"code_sha256_prefix":"d3ccc4988979917b","entry":"r2_difference","repo":"ebrahimfeghhi/beyond-brainscore","repo_kind":"official","path":"misc_code/stats_testing_funcs.py","file_url":"https://github.com/ebrahimfeghhi/beyond-brainscore/blob/HEAD/misc_code/stats_testing_funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3ccc4988979917b"}},{"code_sha256_prefix":"d089027452af38fb","entry":"separate_words_commas_periods","repo":"ebrahimfeghhi/beyond-brainscore","repo_kind":"official","path":"generate_activations/interp_funcs.py","file_url":"https://github.com/ebrahimfeghhi/beyond-brainscore/blob/HEAD/generate_activations/interp_funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d089027452af38fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}