{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZYUZ2CJCNSTPSVQBRLBVFAQADN","short_pith_number":"pith:ZYUZ2CJC","schema_version":"1.0","canonical_sha256":"ce299d09226ca6f956018ac35282001b569ef482a041c058511384bce7963058","source":{"kind":"arxiv","id":"2405.06064","version":1},"attestation_state":"computed","paper":{"title":"LLMs for XAI: Future Directions for Explaining Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alexandra Zytek, Kalyan Veeramachaneni, Sara Pid\\`o","submitted_at":"2024-05-09T19:17:47Z","abstract_excerpt":"In response to the demand for Explainable Artificial Intelligence (XAI), we investigate the use of Large Language Models (LLMs) to transform ML explanations into natural, human-readable narratives. Rather than directly explaining ML models using LLMs, we focus on refining explanations computed using existing XAI algorithms. We outline several research directions, including defining evaluation metrics, prompt design, comparing LLM models, exploring further training methods, and integrating external data. Initial experiments and user study suggest that LLMs offer a promising way to enhance the i"},"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":"2405.06064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-09T19:17:47Z","cross_cats_sorted":["cs.CL","cs.HC","cs.LG"],"title_canon_sha256":"87ac1dce08e9ec91fa7ca257db3c8b16dd6920bf80fdb95984d0a5a32f0419bf","abstract_canon_sha256":"5135454e5b8132177550c01bc6b56c4d1bf6ab02d7ce5c4d360e9862f05073e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:34.837451Z","signature_b64":"PtxOQoBIpobmQe9jMF08d/wTLCs4MI50Y6NTIC0cUSrq3OghSgEYp0aUy2gkQS3IK52omjtKGlqpU9PUV4UMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce299d09226ca6f956018ac35282001b569ef482a041c058511384bce7963058","last_reissued_at":"2026-07-05T08:17:34.837056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:34.837056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs for XAI: Future Directions for Explaining Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alexandra Zytek, Kalyan Veeramachaneni, Sara Pid\\`o","submitted_at":"2024-05-09T19:17:47Z","abstract_excerpt":"In response to the demand for Explainable Artificial Intelligence (XAI), we investigate the use of Large Language Models (LLMs) to transform ML explanations into natural, human-readable narratives. Rather than directly explaining ML models using LLMs, we focus on refining explanations computed using existing XAI algorithms. We outline several research directions, including defining evaluation metrics, prompt design, comparing LLM models, exploring further training methods, and integrating external data. Initial experiments and user study suggest that LLMs offer a promising way to enhance the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06064","kind":"arxiv","version":1},"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/2405.06064/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":"2405.06064","created_at":"2026-07-05T08:17:34.837108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06064v1","created_at":"2026-07-05T08:17:34.837108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06064","created_at":"2026-07-05T08:17:34.837108+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYUZ2CJCNSTP","created_at":"2026-07-05T08:17:34.837108+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYUZ2CJCNSTPSVQB","created_at":"2026-07-05T08:17:34.837108+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYUZ2CJC","created_at":"2026-07-05T08:17:34.837108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01189","citing_title":"NEURON: A Neuro-symbolic System for Grounded Clinical Explainability","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26770","citing_title":"Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13658","citing_title":"Why is \"Chicago\" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01189","citing_title":"NEURON: A Neuro-symbolic System for Grounded Clinical Explainability","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12543","citing_title":"A Two-Stage LLM Framework for Accessible and Verified XAI Explanations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN","json":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN.json","graph_json":"https://pith.science/api/pith-number/ZYUZ2CJCNSTPSVQBRLBVFAQADN/graph.json","events_json":"https://pith.science/api/pith-number/ZYUZ2CJCNSTPSVQBRLBVFAQADN/events.json","paper":"https://pith.science/paper/ZYUZ2CJC"},"agent_actions":{"view_html":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN","download_json":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN.json","view_paper":"https://pith.science/paper/ZYUZ2CJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06064&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYUZ2CJCNSTPSVQBRLBVFAQADN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYUZ2CJCNSTPSVQBRLBVFAQADN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN/action/storage_attestation","attest_author":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN/action/author_attestation","sign_citation":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN/action/citation_signature","submit_replication":"https://pith.science/pith/ZYUZ2CJCNSTPSVQBRLBVFAQADN/action/replication_record"}},"created_at":"2026-07-05T08:17:34.837108+00:00","updated_at":"2026-07-05T08:17:34.837108+00:00"}