{"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/exploring-counterfactual-alignment-loss","title":"Exploring Counterfactual Alignment Loss towards Human-centered AI","arxiv_id":"2310.01766","date":"2023-10-03","proceeding":null,"authors":["Mingzhou Liu","Xinwei Sun","Ching-Wen Lee","Yu Qiao","Yizhou Wang"],"abstract":"Deep neural networks have demonstrated impressive accuracy in supervised learning tasks. However, their lack of transparency makes it hard for humans to trust their results, especially in safe-critic domains such as healthcare. To address this issue, recent explanation-guided learning approaches proposed to align the gradient-based attention map to image regions annotated by human experts, thereby obtaining an intrinsically human-centered model. However, the attention map these methods are based on may fail to causally attribute the model predictions, thus compromising their validity for alignment. To address this issue, we propose a novel human-centered framework based on counterfactual generation. In particular, we utilize the counterfactual generation's ability for causal attribution to introduce a novel loss called the CounterFactual Alignment (CF-Align) loss. This loss guarantees that the features attributed by the counterfactual generation for the classifier align with the human annotations. To optimize the proposed loss that entails a counterfactual generation with an implicit function form, we leverage the implicit function theorem for backpropagation. Our method is architecture-agnostic and, therefore can be applied to any neural network. We demonstrate the effectiveness of our method on a lung cancer diagnosis dataset, showcasing faithful alignment to humans.","url_abs":"https://arxiv.org/abs/2310.01766v1","url_pdf":"https://arxiv.org/pdf/2310.01766v1.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"lung-cancer-diagnosis","task_name":"Lung Cancer Diagnosis"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01766"}},"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":"deterministic:regex_extraction","url":"https://github.com/lmz123321/Causal_alignment","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"found_in_text":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"a0121e0634223a88","entry":"dice_coeff","repo":"lmz123321/Causal_alignment","repo_kind":"found_in_text","path":"DDSM/loss/loss.py","file_url":"https://github.com/lmz123321/Causal_alignment/blob/HEAD/DDSM/loss/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0121e0634223a88"}},{"code_sha256_prefix":"1343a534202417dc","entry":"dice_loss","repo":"lmz123321/Causal_alignment","repo_kind":"found_in_text","path":"DDSM/loss/loss.py","file_url":"https://github.com/lmz123321/Causal_alignment/blob/HEAD/DDSM/loss/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1343a534202417dc"}},{"code_sha256_prefix":"bd9ae1d5528a37a0","entry":"multiclass_dice_coeff","repo":"lmz123321/Causal_alignment","repo_kind":"found_in_text","path":"DDSM/loss/loss.py","file_url":"https://github.com/lmz123321/Causal_alignment/blob/HEAD/DDSM/loss/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd9ae1d5528a37a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}