{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KTHXHADBDMWWHGFSOKSUXJWQAO","short_pith_number":"pith:KTHXHADB","schema_version":"1.0","canonical_sha256":"54cf7380611b2d6398b272a54ba6d003a51a9c441420f02d76457bfccdde8f21","source":{"kind":"arxiv","id":"2310.11207","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Leilani H. Gilpin, Shiyuan Huang, Shreedhar Jangam, Siddarth Mamidanna, Yilun Zhou","submitted_at":"2023-10-17T12:34:32Z","abstract_excerpt":"Large language models (LLMs) such as ChatGPT have demonstrated superior performance on a variety of natural language processing (NLP) tasks including sentiment analysis, mathematical reasoning and summarization. Furthermore, since these models are instruction-tuned on human conversations to produce \"helpful\" responses, they can and often will produce explanations along with the response, which we call self-explanations. For example, when analyzing the sentiment of a movie review, the model may output not only the positivity of the sentiment, but also an explanation (e.g., by listing the sentim"},"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":"2310.11207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T12:34:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9ff43c6421dcf7d038f4443d0b1f87f799d6b465a901162f93e1bd2076244dca","abstract_canon_sha256":"d585865ed65143173b296cf2e8b07b1769df3989c117393f069495384d04a77f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:52.389199Z","signature_b64":"+1EeyN5sPy+Mte/Pzuowmkt5nJkhaz377MBxYkBh3HVraOkWpqm4Jq9kl/KaZmpI/XMfaojs78Cc8pZX/bFuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54cf7380611b2d6398b272a54ba6d003a51a9c441420f02d76457bfccdde8f21","last_reissued_at":"2026-07-05T07:01:52.388832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:52.388832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Leilani H. Gilpin, Shiyuan Huang, Shreedhar Jangam, Siddarth Mamidanna, Yilun Zhou","submitted_at":"2023-10-17T12:34:32Z","abstract_excerpt":"Large language models (LLMs) such as ChatGPT have demonstrated superior performance on a variety of natural language processing (NLP) tasks including sentiment analysis, mathematical reasoning and summarization. Furthermore, since these models are instruction-tuned on human conversations to produce \"helpful\" responses, they can and often will produce explanations along with the response, which we call self-explanations. For example, when analyzing the sentiment of a movie review, the model may output not only the positivity of the sentiment, but also an explanation (e.g., by listing the sentim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11207","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/2310.11207/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":"2310.11207","created_at":"2026-07-05T07:01:52.388887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11207v1","created_at":"2026-07-05T07:01:52.388887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11207","created_at":"2026-07-05T07:01:52.388887+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTHXHADBDMWW","created_at":"2026-07-05T07:01:52.388887+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTHXHADBDMWWHGFS","created_at":"2026-07-05T07:01:52.388887+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTHXHADB","created_at":"2026-07-05T07:01:52.388887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01210","citing_title":"Can we trust LLM Self-Explanations for Entity Resolution?","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28615","citing_title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24727","citing_title":"Fundamental Limitation in Explaining AI","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23591","citing_title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2410.03296","citing_title":"A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19775","citing_title":"From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12139","citing_title":"BoolXLLM: LLM-Assisted Explainability for Boolean Models","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO","json":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO.json","graph_json":"https://pith.science/api/pith-number/KTHXHADBDMWWHGFSOKSUXJWQAO/graph.json","events_json":"https://pith.science/api/pith-number/KTHXHADBDMWWHGFSOKSUXJWQAO/events.json","paper":"https://pith.science/paper/KTHXHADB"},"agent_actions":{"view_html":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO","download_json":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO.json","view_paper":"https://pith.science/paper/KTHXHADB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11207&json=true","fetch_graph":"https://pith.science/api/pith-number/KTHXHADBDMWWHGFSOKSUXJWQAO/graph.json","fetch_events":"https://pith.science/api/pith-number/KTHXHADBDMWWHGFSOKSUXJWQAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO/action/storage_attestation","attest_author":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO/action/author_attestation","sign_citation":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO/action/citation_signature","submit_replication":"https://pith.science/pith/KTHXHADBDMWWHGFSOKSUXJWQAO/action/replication_record"}},"created_at":"2026-07-05T07:01:52.388887+00:00","updated_at":"2026-07-05T07:01:52.388887+00:00"}