{"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/multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","arxiv_id":"2407.02273","date":"2024-07-02","proceeding":null,"authors":["Zhijing Jin","Max Kleiman-Weiner","Giorgio Piatti","Sydney Levine","Jiarui Liu","Fernando Gonzalez","Francesco Ortu","András Strausz","Mrinmaya Sachan","Rada Mihalcea","Yejin Choi","Bernhard Schölkopf"],"abstract":"We evaluate the moral alignment of large language models (LLMs) with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP. This dataset enables the assessment of LLMs' decision-making processes in diverse linguistic contexts. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions: species, gender, fitness, status, age, and the number of lives involved. By correlating these preferences with the demographic distribution of language speakers and examining the consistency of LLM responses to various prompt paraphrasings, our findings provide insights into cross-lingual and ethical biases of LLMs and their intersection. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems and highlighting the importance of incorporating diverse perspectives in AI ethics. The results underscore the need for further research on the integration of multilingual dimensions in responsible AI research to ensure fair and equitable AI interactions worldwide. Our code and data are at https://github.com/causalNLP/moralmachine","url_abs":"https://arxiv.org/abs/2407.02273v5","url_pdf":"https://arxiv.org/pdf/2407.02273v5.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":"multilingual-trolley-problems-for-language","repo_url":"https://github.com/causalNLP/moralmachine","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multilingual-trolley-problems-for-language","repo_url":"https://github.com/causalnlp/multitp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"ethics","task_name":"Ethics"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.02273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02273"}},"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/causalNLP/moralmachine","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/causalnlp/multitp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":"51b748076654186d","entry":"get_model_release_date","repo":"causalNLP/moralmachine","repo_kind":"official","path":"multi_tp/models_ids.py","file_url":"https://github.com/causalNLP/moralmachine/blob/HEAD/multi_tp/models_ids.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51b748076654186d"}},{"code_sha256_prefix":"bf351864d0daa92c","entry":"get_size","repo":"causalNLP/moralmachine","repo_kind":"official","path":"multi_tp/models_ids.py","file_url":"https://github.com/causalNLP/moralmachine/blob/HEAD/multi_tp/models_ids.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf351864d0daa92c"}},{"code_sha256_prefix":"04ea8f490ac507f8","entry":"parse_dict_from_json","repo":"causalNLP/moralmachine","repo_kind":"official","path":"code/run_llama.py","file_url":"https://github.com/causalNLP/moralmachine/blob/HEAD/code/run_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04ea8f490ac507f8"}},{"code_sha256_prefix":"bf7c01cef3555b12","entry":"get_family","repo":"causalNLP/moralmachine","repo_kind":"official","path":"multi_tp/models_ids.py","file_url":"https://github.com/causalNLP/moralmachine/blob/HEAD/multi_tp/models_ids.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf7c01cef3555b12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}