{"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/symdpo-boosting-in-context-learning-of-large","title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","arxiv_id":"2411.11909","date":"2024-11-17","proceeding":"CVPR 2025 1","authors":["Hongrui Jia","Chaoya Jiang","Haiyang Xu","Wei Ye","Mengfan Dong","Ming Yan","Ji Zhang","Fei Huang","Shikun Zhang"],"abstract":"As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, existing LMMs face a critical issue: they often fail to effectively leverage the visual context in multimodal demonstrations and instead simply follow textual patterns. This indicates that LMMs do not achieve effective alignment between multimodal demonstrations and model outputs. To address this problem, we propose Symbol Demonstration Direct Preference Optimization (SymDPO). Specifically, SymDPO aims to break the traditional paradigm of constructing multimodal demonstrations by using random symbols to replace text answers within instances. This forces the model to carefully understand the demonstration images and establish a relationship between the images and the symbols to answer questions correctly. We validate the effectiveness of this method on multiple benchmarks, demonstrating that with SymDPO, LMMs can more effectively understand the multimodal context within examples and utilize this knowledge to answer questions better.","url_abs":"https://arxiv.org/abs/2411.11909v1","url_pdf":"https://arxiv.org/pdf/2411.11909v1.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":"symdpo-boosting-in-context-learning-of-large","repo_url":"https://github.com/APiaoG/SymDPO","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11909"}},"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/APiaoG/SymDPO","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":8,"samples":[{"code_sha256_prefix":"4d75570b4e91d0b4","entry":"FeedForward","repo":"APiaoG/SymDPO","repo_kind":"official","path":"open_flamingo/src/helpers.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/open_flamingo/src/helpers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d75570b4e91d0b4"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"APiaoG/SymDPO","repo_kind":"official","path":"open_flamingo/src/helpers.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/open_flamingo/src/helpers.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"c32b636f13ed9ee5","entry":"convert_to_scalar","repo":"APiaoG/SymDPO","repo_kind":"official","path":"trl/core.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/trl/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c32b636f13ed9ee5"}},{"code_sha256_prefix":"0861aab202cd8f62","entry":"flash_attn_fn","repo":"APiaoG/SymDPO","repo_kind":"official","path":"open_flamingo/src/attention.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/open_flamingo/src/attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0861aab202cd8f62"}},{"code_sha256_prefix":"a51ae45a1f6c0b5b","entry":"flatten_dict","repo":"APiaoG/SymDPO","repo_kind":"official","path":"trl/core.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/trl/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a51ae45a1f6c0b5b"}},{"code_sha256_prefix":"41f09d65a32dd8bc","entry":"scaled_multihead_dot_product_attention","repo":"APiaoG/SymDPO","repo_kind":"official","path":"open_flamingo/src/attention.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/open_flamingo/src/attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41f09d65a32dd8bc"}},{"code_sha256_prefix":"2c3da386578af970","entry":"top_k_top_p_filtering","repo":"APiaoG/SymDPO","repo_kind":"official","path":"trl/core.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/trl/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c3da386578af970"}},{"code_sha256_prefix":"b311f25d750d0626","entry":"triton_flash_attn_fn","repo":"APiaoG/SymDPO","repo_kind":"official","path":"open_flamingo/src/attention.py","file_url":"https://github.com/APiaoG/SymDPO/blob/HEAD/open_flamingo/src/attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b311f25d750d0626"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}