{"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/a-glitch-in-the-matrix-locating-and-detecting","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","arxiv_id":"2312.02073","date":"2023-12-04","proceeding":null,"authors":["Giovanni Monea","Maxime Peyrard","Martin Josifoski","Vishrav Chaudhary","Jason Eisner","Emre Kiciman","Hamid Palangi","Barun Patra","Robert West"],"abstract":"Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling. Favoring the contextual information is critical for retrieval-augmented generation methods, which enrich the context with up-to-date information, hoping that grounding can rectify outdated or noisy stored knowledge. We present a novel method to study grounding abilities using Fakepedia, a novel dataset of counterfactual texts constructed to clash with a model's internal parametric knowledge. In this study, we introduce Fakepedia, a counterfactual dataset designed to evaluate grounding abilities when the internal parametric knowledge clashes with the contextual information. We benchmark various LLMs with Fakepedia and conduct a causal mediation analysis of LLM components when answering Fakepedia queries, based on our Masked Grouped Causal Tracing (MGCT) method. Through this analysis, we identify distinct computational patterns between grounded and ungrounded responses. We finally demonstrate that distinguishing grounded from ungrounded responses is achievable through computational analysis alone. Our results, together with existing findings about factual recall mechanisms, provide a coherent narrative of how grounding and factual recall mechanisms interact within LLMs.","url_abs":"https://arxiv.org/abs/2312.02073v3","url_pdf":"https://arxiv.org/pdf/2312.02073v3.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":"a-glitch-in-the-matrix-locating-and-detecting","repo_url":"https://github.com/epfl-dlab/llm-grounding-analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.02073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02073"}},"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/epfl-dlab/llm-grounding-analysis","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"e16afd9ac401996f","entry":"adapt_target_tokens","repo":"epfl-dlab/llm-grounding-analysis","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/epfl-dlab/llm-grounding-analysis/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e16afd9ac401996f"}},{"code_sha256_prefix":"5c049e9aa7881e58","entry":"get_next_token","repo":"epfl-dlab/llm-grounding-analysis","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/epfl-dlab/llm-grounding-analysis/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c049e9aa7881e58"}},{"code_sha256_prefix":"c9cbe06f9880641d","entry":"split_text","repo":"epfl-dlab/llm-grounding-analysis","repo_kind":"official","path":"filter_data.py","file_url":"https://github.com/epfl-dlab/llm-grounding-analysis/blob/HEAD/filter_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9cbe06f9880641d"}},{"code_sha256_prefix":"8b8e9e37dbc4b188","entry":"get_next_token_probabilities","repo":"epfl-dlab/llm-grounding-analysis","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/epfl-dlab/llm-grounding-analysis/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b8e9e37dbc4b188"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}