{"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/characterizing-truthfulness-in-large-language","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","arxiv_id":"2402.18048","date":"2024-02-28","proceeding":null,"authors":["Fan Yin","Jayanth Srinivasa","Kai-Wei Chang"],"abstract":"We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs. Although several approaches based on entropy or verbalized uncertainty have been proposed to calibrate model predictions, these methods are often intractable, sensitive to hyperparameters, and less reliable when applied in generative tasks with LLMs. In this paper, we suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations. Through experiments on four question answering (QA) datasets, we demonstrate the effectiveness ohttps://info.arxiv.org/help/prep#abstractsf our proposed method. Additionally, we study intrinsic dimensions in LLMs and their relations with model layers, autoregressive language modeling, and the training of LLMs, revealing that intrinsic dimensions can be a powerful approach to understanding LLMs.","url_abs":"https://arxiv.org/abs/2402.18048v1","url_pdf":"https://arxiv.org/pdf/2402.18048v1.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":"characterizing-truthfulness-in-large-language","repo_url":"https://github.com/fanyin3639/lid-hallucinationdetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.18048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18048"}},"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/fanyin3639/lid-hallucinationdetection","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"4368c60a0d653eeb","entry":"compute_lid","repo":"fanyin3639/lid-hallucinationdetection","repo_kind":"official","path":"src/lids.py","file_url":"https://github.com/fanyin3639/lid-hallucinationdetection/blob/HEAD/src/lids.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4368c60a0d653eeb"}},{"code_sha256_prefix":"3ecc57c8205e4510","entry":"construct_input","repo":"fanyin3639/lid-hallucinationdetection","repo_kind":"official","path":"src/get_activation.py","file_url":"https://github.com/fanyin3639/lid-hallucinationdetection/blob/HEAD/src/get_activation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ecc57c8205e4510"}},{"code_sha256_prefix":"9a71eba082ec07de","entry":"f1_score","repo":"fanyin3639/lid-hallucinationdetection","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/fanyin3639/lid-hallucinationdetection/blob/HEAD/src/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a71eba082ec07de"}},{"code_sha256_prefix":"4e686c57f3e71d5f","entry":"normalize_text","repo":"fanyin3639/lid-hallucinationdetection","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/fanyin3639/lid-hallucinationdetection/blob/HEAD/src/metrics.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4e686c57f3e71d5f"}},{"code_sha256_prefix":"5500940dd53a6735","entry":"construct_new_output","repo":"fanyin3639/lid-hallucinationdetection","repo_kind":"official","path":"src/get_activation.py","file_url":"https://github.com/fanyin3639/lid-hallucinationdetection/blob/HEAD/src/get_activation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5500940dd53a6735"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}