{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sight-beyond-text-multi-modal-training","title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","arxiv_id":"2309.07120","date":"2023-09-13","proceeding":null,"authors":["Haoqin Tu","Bingchen Zhao","Chen Wei","Cihang Xie"],"abstract":"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 alignment in the pure NLP context. For example, a visual-instruction-tuned LLaMA2 7B model surpasses the performance of the LLaMA2-chat 7B model, fine-tuned with over one million human annotations, on TruthfulQA-mc and Ethics benchmarks. Further analysis reveals that the improved alignment can be attributed to the superior instruction quality inherent to visual-text data. In releasing our code at github.com/UCSC-VLAA/Sight-Beyond-Text, we aspire to foster further exploration into the intrinsic value of visual-text synergies and, in a broader scope, multi-modal interactions in alignment research.","url_abs":"https://arxiv.org/abs/2309.07120v1","url_pdf":"https://arxiv.org/pdf/2309.07120v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sight-beyond-text-multi-modal-training","repo_url":"https://github.com/ucsc-vlaa/sight-beyond-text","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"ethics","task_name":"Ethics"},{"task_slug":"truthfulqa","task_name":"TruthfulQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.07120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07120"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ucsc-vlaa/sight-beyond-text","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3ab3c57755867f9a","entry":"find_layers","repo":"ucsc-vlaa/sight-beyond-text","repo_kind":"official","path":"llava/eval/mmlu/mmlu_modeling.py","file_url":"https://github.com/ucsc-vlaa/sight-beyond-text/blob/HEAD/llava/eval/mmlu/mmlu_modeling.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab3c57755867f9a"}},{"code_sha256_prefix":"c3ee9d07c900dd55","entry":"load_image_from_base64","repo":"ucsc-vlaa/sight-beyond-text","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/ucsc-vlaa/sight-beyond-text/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3ee9d07c900dd55"}},{"code_sha256_prefix":"1df990c375318896","entry":"process_images","repo":"ucsc-vlaa/sight-beyond-text","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/ucsc-vlaa/sight-beyond-text/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1df990c375318896"}},{"code_sha256_prefix":"ba7f40ab714e8d9c","entry":"load_quant","repo":"ucsc-vlaa/sight-beyond-text","repo_kind":"official","path":"llava/eval/mmlu/mmlu_modeling.py","file_url":"https://github.com/ucsc-vlaa/sight-beyond-text/blob/HEAD/llava/eval/mmlu/mmlu_modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba7f40ab714e8d9c"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"ucsc-vlaa/sight-beyond-text","repo_kind":"official","path":"llava/utils.py","file_url":"https://github.com/ucsc-vlaa/sight-beyond-text/blob/HEAD/llava/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37899f22fb191b37"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"ucsc-vlaa/sight-beyond-text","repo_kind":"official","path":"llava/utils.py","file_url":"https://github.com/ucsc-vlaa/sight-beyond-text/blob/HEAD/llava/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}