{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ASXSCR3EL2UQRQIXB3DEWWBXI6","short_pith_number":"pith:ASXSCR3E","schema_version":"1.0","canonical_sha256":"04af2147645ea908c1170ec64b583747a06d1bfef4cb2e07c7da8e78e2e83aa5","source":{"kind":"arxiv","id":"2409.11242","version":4},"attestation_state":"computed","paper":{"title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Leong Chieu, Maojia Song, Navonil Majumder, Rishabh Bhardwaj, Shang Hong Sim, Soujanya Poria","submitted_at":"2024-09-17T14:47:33Z","abstract_excerpt":"LLMs are an integral component of retrieval-augmented generation (RAG) systems. While many studies focus on evaluating the overall quality of end-to-end RAG systems, there is a gap in understanding the appropriateness of LLMs for the RAG task. To address this, we introduce Trust-Score, a holistic metric that evaluates the trustworthiness of LLMs within the RAG framework. Our results show that various prompting methods, such as in-context learning, fail to effectively adapt LLMs to the RAG task as measured by Trust-Score. Consequently, we propose Trust-Align, a method to align LLMs for improved"},"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":"2409.11242","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:47:33Z","cross_cats_sorted":[],"title_canon_sha256":"719e14f618b4aa606590dea41aa9f79c6f4a6c6a3cdd0671a548157abdf55c2f","abstract_canon_sha256":"8ccdab060d9ad0c15930817145df1c2c25c6389c1047ee2999a16186dae7c34b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:11.819269Z","signature_b64":"e8qAr5DjaMmR4Rtp0ZGF6nsslqrhjyUfwnUFq1q2+dbV9Fk4zNujSmym+rnJqMFnakflh1WfoSsa5VQAo/vWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04af2147645ea908c1170ec64b583747a06d1bfef4cb2e07c7da8e78e2e83aa5","last_reissued_at":"2026-07-05T10:53:11.818785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:11.818785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Leong Chieu, Maojia Song, Navonil Majumder, Rishabh Bhardwaj, Shang Hong Sim, Soujanya Poria","submitted_at":"2024-09-17T14:47:33Z","abstract_excerpt":"LLMs are an integral component of retrieval-augmented generation (RAG) systems. While many studies focus on evaluating the overall quality of end-to-end RAG systems, there is a gap in understanding the appropriateness of LLMs for the RAG task. To address this, we introduce Trust-Score, a holistic metric that evaluates the trustworthiness of LLMs within the RAG framework. Our results show that various prompting methods, such as in-context learning, fail to effectively adapt LLMs to the RAG task as measured by Trust-Score. Consequently, we propose Trust-Align, a method to align LLMs for improved"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11242","kind":"arxiv","version":4},"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/2409.11242/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":"2409.11242","created_at":"2026-07-05T10:53:11.818849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11242v4","created_at":"2026-07-05T10:53:11.818849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11242","created_at":"2026-07-05T10:53:11.818849+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASXSCR3EL2UQ","created_at":"2026-07-05T10:53:11.818849+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASXSCR3EL2UQRQIX","created_at":"2026-07-05T10:53:11.818849+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASXSCR3E","created_at":"2026-07-05T10:53:11.818849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19292","citing_title":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6","json":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6.json","graph_json":"https://pith.science/api/pith-number/ASXSCR3EL2UQRQIXB3DEWWBXI6/graph.json","events_json":"https://pith.science/api/pith-number/ASXSCR3EL2UQRQIXB3DEWWBXI6/events.json","paper":"https://pith.science/paper/ASXSCR3E"},"agent_actions":{"view_html":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6","download_json":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6.json","view_paper":"https://pith.science/paper/ASXSCR3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11242&json=true","fetch_graph":"https://pith.science/api/pith-number/ASXSCR3EL2UQRQIXB3DEWWBXI6/graph.json","fetch_events":"https://pith.science/api/pith-number/ASXSCR3EL2UQRQIXB3DEWWBXI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6/action/storage_attestation","attest_author":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6/action/author_attestation","sign_citation":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6/action/citation_signature","submit_replication":"https://pith.science/pith/ASXSCR3EL2UQRQIXB3DEWWBXI6/action/replication_record"}},"created_at":"2026-07-05T10:53:11.818849+00:00","updated_at":"2026-07-05T10:53:11.818849+00:00"}