{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MLAUHYGDHUVZ6UQ57AYTWIX4K6","short_pith_number":"pith:MLAUHYGD","schema_version":"1.0","canonical_sha256":"62c143e0c33d2b9f521df8313b22fc57ac76498a786054f0451591c1e998bf44","source":{"kind":"arxiv","id":"2401.12874","version":2},"attestation_state":"computed","paper":{"title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoyan Luo, Lucia Specia","submitted_at":"2024-01-23T16:09:53Z","abstract_excerpt":"Explainability for Large Language Models (LLMs) is a critical yet challenging aspect of natural language processing. As LLMs are increasingly integral to diverse applications, their \"black-box\" nature sparks significant concerns regarding transparency and ethical use. This survey underscores the imperative for increased explainability in LLMs, delving into both the research on explainability and the various methodologies and tasks that utilize an understanding of these models. Our focus is primarily on pre-trained Transformer-based LLMs, such as LLaMA family, which pose distinctive interpretab"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.12874","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T16:09:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2362f3875cd483dda5a891809506fa3d904d6bf11e124fe1fb44a51de60948ed","abstract_canon_sha256":"b992aa9c62c4f3db26cc700705fa2860613155b1a5da3717f8162cba3e9af808"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:02.814654Z","signature_b64":"zTSDgtUgBqYGeOX42BZYeXepz+DNEg0fAIKjiWEG2TCVTlg0Ajso/0XskQn2HsLJdLSOgHFA9wJOayyVRwaiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c143e0c33d2b9f521df8313b22fc57ac76498a786054f0451591c1e998bf44","last_reissued_at":"2026-07-05T07:48:02.814134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:02.814134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoyan Luo, Lucia Specia","submitted_at":"2024-01-23T16:09:53Z","abstract_excerpt":"Explainability for Large Language Models (LLMs) is a critical yet challenging aspect of natural language processing. As LLMs are increasingly integral to diverse applications, their \"black-box\" nature sparks significant concerns regarding transparency and ethical use. This survey underscores the imperative for increased explainability in LLMs, delving into both the research on explainability and the various methodologies and tasks that utilize an understanding of these models. Our focus is primarily on pre-trained Transformer-based LLMs, such as LLaMA family, which pose distinctive interpretab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12874","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.12874/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.12874","created_at":"2026-07-05T07:48:02.814197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12874v2","created_at":"2026-07-05T07:48:02.814197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12874","created_at":"2026-07-05T07:48:02.814197+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLAUHYGDHUVZ","created_at":"2026-07-05T07:48:02.814197+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLAUHYGDHUVZ6UQ5","created_at":"2026-07-05T07:48:02.814197+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLAUHYGD","created_at":"2026-07-05T07:48:02.814197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03085","citing_title":"Multi-component Causal Tracing in Large Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15411","citing_title":"Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12439","citing_title":"Multi-agent Self-triage System with Medical Flowcharts","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14004","citing_title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","ref_index":200,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06342","citing_title":"Don't Lose Focus: Activation Steering via Key-Orthogonal Projections","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06695","citing_title":"Reasoning Fails Where Step Flow Breaks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17761","citing_title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6","json":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6.json","graph_json":"https://pith.science/api/pith-number/MLAUHYGDHUVZ6UQ57AYTWIX4K6/graph.json","events_json":"https://pith.science/api/pith-number/MLAUHYGDHUVZ6UQ57AYTWIX4K6/events.json","paper":"https://pith.science/paper/MLAUHYGD"},"agent_actions":{"view_html":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6","download_json":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6.json","view_paper":"https://pith.science/paper/MLAUHYGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12874&json=true","fetch_graph":"https://pith.science/api/pith-number/MLAUHYGDHUVZ6UQ57AYTWIX4K6/graph.json","fetch_events":"https://pith.science/api/pith-number/MLAUHYGDHUVZ6UQ57AYTWIX4K6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6/action/storage_attestation","attest_author":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6/action/author_attestation","sign_citation":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6/action/citation_signature","submit_replication":"https://pith.science/pith/MLAUHYGDHUVZ6UQ57AYTWIX4K6/action/replication_record"}},"created_at":"2026-07-05T07:48:02.814197+00:00","updated_at":"2026-07-05T07:48:02.814197+00:00"}