{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YPFAA6MGVFPETBJEY3D37UVZVZ","short_pith_number":"pith:YPFAA6MG","schema_version":"1.0","canonical_sha256":"c3ca007986a95e498524c6c7bfd2b9ae43a25d81cd5f8af85e2bbc1bca245572","source":{"kind":"arxiv","id":"2309.07120","version":1},"attestation_state":"computed","paper":{"title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bingchen Zhao, Chen Wei, Cihang Xie, Haoqin Tu","submitted_at":"2023-09-13T17:57:21Z","abstract_excerpt":"Multi-modal large language models (MLLMs) are trained based on large language models (LLM), with an enhanced capability to comprehend multi-modal inputs and generate textual responses. While they excel in multi-modal tasks, the pure NLP abilities of MLLMs are often underestimated and left untested. In this study, we get out of the box and unveil an intriguing characteristic of MLLMs -- our preliminary results suggest that visual instruction tuning, a prevailing strategy for transitioning LLMs into MLLMs, unexpectedly and interestingly helps models attain both improved truthfulness and ethical "},"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":"2309.07120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-13T17:57:21Z","cross_cats_sorted":["cs.AI","cs.CV","cs.CY","cs.LG"],"title_canon_sha256":"4f0acabdbc0f26b1f9ad239465e4bdca6ce0de82aef3f41e853b43b96c986b3d","abstract_canon_sha256":"59c4c41a9a38deee9b2f12dd44710407cdc75eea0ac8c7cb4855a292e9a04e69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:26.675827Z","signature_b64":"FfxxCo/ZevrVvPOO95kVvm8uWDOFQItIzHPW067DDFNbZvqs7u8yr8E1Koe9SDoPgh3XtPMMzM6hYauQWToXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3ca007986a95e498524c6c7bfd2b9ae43a25d81cd5f8af85e2bbc1bca245572","last_reissued_at":"2026-07-05T06:50:26.675331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:26.675331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bingchen Zhao, Chen Wei, Cihang Xie, Haoqin Tu","submitted_at":"2023-09-13T17:57:21Z","abstract_excerpt":"Multi-modal large language models (MLLMs) are trained based on large language models (LLM), with an enhanced capability to comprehend multi-modal inputs and generate textual responses. While they excel in multi-modal tasks, the pure NLP abilities of MLLMs are often underestimated and left untested. In this study, we get out of the box and unveil an intriguing characteristic of MLLMs -- our preliminary results suggest that visual instruction tuning, a prevailing strategy for transitioning LLMs into MLLMs, unexpectedly and interestingly helps models attain both improved truthfulness and ethical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07120","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/2309.07120/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":"2309.07120","created_at":"2026-07-05T06:50:26.675391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07120v1","created_at":"2026-07-05T06:50:26.675391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07120","created_at":"2026-07-05T06:50:26.675391+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPFAA6MGVFPE","created_at":"2026-07-05T06:50:26.675391+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPFAA6MGVFPETBJE","created_at":"2026-07-05T06:50:26.675391+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPFAA6MG","created_at":"2026-07-05T06:50:26.675391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ","json":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ.json","graph_json":"https://pith.science/api/pith-number/YPFAA6MGVFPETBJEY3D37UVZVZ/graph.json","events_json":"https://pith.science/api/pith-number/YPFAA6MGVFPETBJEY3D37UVZVZ/events.json","paper":"https://pith.science/paper/YPFAA6MG"},"agent_actions":{"view_html":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ","download_json":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ.json","view_paper":"https://pith.science/paper/YPFAA6MG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07120&json=true","fetch_graph":"https://pith.science/api/pith-number/YPFAA6MGVFPETBJEY3D37UVZVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YPFAA6MGVFPETBJEY3D37UVZVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ/action/storage_attestation","attest_author":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ/action/author_attestation","sign_citation":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ/action/citation_signature","submit_replication":"https://pith.science/pith/YPFAA6MGVFPETBJEY3D37UVZVZ/action/replication_record"}},"created_at":"2026-07-05T06:50:26.675391+00:00","updated_at":"2026-07-05T06:50:26.675391+00:00"}