{"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/emergent-world-models-and-latent-variable","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","arxiv_id":"2403.15498","date":"2024-03-21","proceeding":null,"authors":["Adam Karvonen"],"abstract":"Language models have shown unprecedented capabilities, sparking debate over the source of their performance. Is it merely the outcome of learning syntactic patterns and surface level statistics, or do they extract semantics and a world model from the text? Prior work by Li et al. investigated this by training a GPT model on synthetic, randomly generated Othello games and found that the model learned an internal representation of the board state. We extend this work into the more complex domain of chess, training on real games and investigating our model's internal representations using linear probes and contrastive activations. The model is given no a priori knowledge of the game and is solely trained on next character prediction, yet we find evidence of internal representations of board state. We validate these internal representations by using them to make interventions on the model's activations and edit its internal board state. Unlike Li et al's prior synthetic dataset approach, our analysis finds that the model also learns to estimate latent variables like player skill to better predict the next character. We derive a player skill vector and add it to the model, improving the model's win rate by up to 2.6 times.","url_abs":"https://arxiv.org/abs/2403.15498v2","url_pdf":"https://arxiv.org/pdf/2403.15498v2.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":"emergent-world-models-and-latent-variable","repo_url":"https://github.com/adamkarvonen/chess_llm_interpretability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.15498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15498"}},"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/adamkarvonen/chess_llm_interpretability","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"454b30168edfa3e2","entry":"board_state_to_RRC","repo":"adamkarvonen/chess_llm_interpretability","repo_kind":"official","path":"othello_utils.py","file_url":"https://github.com/adamkarvonen/chess_llm_interpretability/blob/HEAD/othello_utils.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":"454b30168edfa3e2"}},{"code_sha256_prefix":"3e75dd405179bd2a","entry":"initialize_output_tracker","repo":"adamkarvonen/chess_llm_interpretability","repo_kind":"official","path":"board_state_interventions.py","file_url":"https://github.com/adamkarvonen/chess_llm_interpretability/blob/HEAD/board_state_interventions.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":"3e75dd405179bd2a"}},{"code_sha256_prefix":"1a0f3a6c603d52ed","entry":"permit","repo":"adamkarvonen/chess_llm_interpretability","repo_kind":"official","path":"othello_engine_utils.py","file_url":"https://github.com/adamkarvonen/chess_llm_interpretability/blob/HEAD/othello_engine_utils.py","link_basis":"harvester_set","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":"1a0f3a6c603d52ed"}},{"code_sha256_prefix":"1484fe530bc561e5","entry":"permit_reverse","repo":"adamkarvonen/chess_llm_interpretability","repo_kind":"official","path":"othello_engine_utils.py","file_url":"https://github.com/adamkarvonen/chess_llm_interpretability/blob/HEAD/othello_engine_utils.py","link_basis":"harvester_set","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":"1484fe530bc561e5"}},{"code_sha256_prefix":"0a2c0f55c57d9f48","entry":"to_board_label","repo":"adamkarvonen/chess_llm_interpretability","repo_kind":"official","path":"othello_engine_utils.py","file_url":"https://github.com/adamkarvonen/chess_llm_interpretability/blob/HEAD/othello_engine_utils.py","link_basis":"harvester_set","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":"0a2c0f55c57d9f48"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}