{"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/quantifying-emergence-in-large-language","title":"Quantifying Semantic Emergence in Language Models","arxiv_id":"2405.12617","date":"2024-05-21","proceeding":null,"authors":["Hang Chen","Xinyu Yang","Jiaying Zhu","Wenya Wang"],"abstract":"Large language models (LLMs) are widely recognized for their exceptional capacity to capture semantics meaning. Yet, there remains no established metric to quantify this capability. In this work, we introduce a quantitative metric, Information Emergence (IE), designed to measure LLMs' ability to extract semantics from input tokens. We formalize ``semantics'' as the meaningful information abstracted from a sequence of tokens and quantify this by comparing the entropy reduction observed for a sequence of tokens (macro-level) and individual tokens (micro-level). To achieve this, we design a lightweight estimator to compute the mutual information at each transformer layer, which is agnostic to different tasks and language model architectures. We apply IE in both synthetic in-context learning (ICL) scenarios and natural sentence contexts. Experiments demonstrate informativeness and patterns about semantics. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights.","url_abs":"https://arxiv.org/abs/2405.12617v2","url_pdf":"https://arxiv.org/pdf/2405.12617v2.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":"quantifying-emergence-in-large-language","repo_url":"https://github.com/zodiark-ch/emergence-of-llms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"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-2","method_name":"GPT-2"},{"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=2405.12617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12617"}},"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/zodiark-ch/emergence-of-llms","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"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":"76791810a73ce23a","entry":"read_json","repo":"zodiark-ch/emergence-of-llms","repo_kind":"official","path":"GEMMA/utils.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/GEMMA/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":"76791810a73ce23a"}},{"code_sha256_prefix":"a3d7a36d8b4073c1","entry":"get_model_layer_num","repo":"zodiark-ch/emergence-of-llms","repo_kind":"official","path":"GEMMA/utils.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/GEMMA/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3d7a36d8b4073c1"}},{"code_sha256_prefix":"97fe543c8f929340","entry":"main","repo":"zodiark-ch/emergence-of-llms","repo_kind":"official","path":"GEMMA/MINE_for_LLMs.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/GEMMA/MINE_for_LLMs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97fe543c8f929340"}},{"code_sha256_prefix":"fdaa46782e6db761","entry":"main","repo":"zodiark-ch/emergence-of-llms","repo_kind":"official","path":"GPT2/MINE_for_LLMs.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/GPT2/MINE_for_LLMs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdaa46782e6db761"}},{"code_sha256_prefix":"b67229533c2ca1ff","entry":"main","repo":"zodiark-ch/emergence-of-llms","repo_kind":"official","path":"OpenLlama/MINE_for_LLMs.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/OpenLlama/MINE_for_LLMs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b67229533c2ca1ff"}},{"code_sha256_prefix":"97bc0a310d350639","entry":"set_default_to_empty_string","repo":"zodiark-ch/emergence-of-llms","repo_kind":"official","path":"GEMMA/utils.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/GEMMA/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97bc0a310d350639"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}