{"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/ethical-advice-taker-do-language-models","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","arxiv_id":"2106.01465","date":"2021-06-02","proceeding":"Findings (ACL) 2021 8","authors":["Jieyu Zhao","Daniel Khashabi","Tushar Khot","Ashish Sabharwal","Kai-Wei Chang"],"abstract":"Is it possible to use natural language to intervene in a model's behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the context of social stereotypes. Specifically, we propose a new language understanding task, Linguistic Ethical Interventions (LEI), where the goal is to amend a question-answering (QA) model's unethical behavior by communicating context-specific principles of ethics and equity to it. To this end, we build upon recent methods for quantifying a system's social stereotypes, augmenting them with different kinds of ethical interventions and the desired model behavior under such interventions. Our zero-shot evaluation finds that even today's powerful neural language models are extremely poor ethical-advice takers, that is, they respond surprisingly little to ethical interventions even though these interventions are stated as simple sentences. Few-shot learning improves model behavior but remains far from the desired outcome, especially when evaluated for various types of generalization. Our new task thus poses a novel language understanding challenge for the community.","url_abs":"https://arxiv.org/abs/2106.01465v1","url_pdf":"https://arxiv.org/pdf/2106.01465v1.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":"ethical-advice-taker-do-language-models","repo_url":"https://github.com/allenai/ethical-interventions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"ethics","task_name":"Ethics"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.01465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01465"}},"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/allenai/ethical-interventions","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"ran":0,"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":"1dd8d8ccbcfefd0f","entry":"cal_same","repo":"allenai/ethical-interventions","repo_kind":"official","path":"get_acc.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/get_acc.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":"1dd8d8ccbcfefd0f"}},{"code_sha256_prefix":"882df10f7336e7d9","entry":"get_ans_p","repo":"allenai/ethical-interventions","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/analysis.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":"882df10f7336e7d9"}},{"code_sha256_prefix":"0154494fec62dfcd","entry":"get_data","repo":"allenai/ethical-interventions","repo_kind":"official","path":"model_select.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/model_select.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":"0154494fec62dfcd"}},{"code_sha256_prefix":"ae4db27c6dd3327c","entry":"get_data","repo":"allenai/ethical-interventions","repo_kind":"official","path":"plot.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/plot.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":"ae4db27c6dd3327c"}},{"code_sha256_prefix":"c60cab71350d2fbc","entry":"get_subj1_win_score","repo":"allenai/ethical-interventions","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/analysis.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":"c60cab71350d2fbc"}},{"code_sha256_prefix":"db2b74b069046e20","entry":"get_tokens","repo":"allenai/ethical-interventions","repo_kind":"official","path":"mutils.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/mutils.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":"db2b74b069046e20"}},{"code_sha256_prefix":"af5389807d8f56a5","entry":"pairup_ex","repo":"allenai/ethical-interventions","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/analysis.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":"af5389807d8f56a5"}},{"code_sha256_prefix":"bda22be74de395aa","entry":"pairup_ex","repo":"allenai/ethical-interventions","repo_kind":"official","path":"ianalysis.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/ianalysis.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":"bda22be74de395aa"}},{"code_sha256_prefix":"53609984a77d7a10","entry":"read_data","repo":"allenai/ethical-interventions","repo_kind":"official","path":"mutils.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/mutils.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":"53609984a77d7a10"}},{"code_sha256_prefix":"bf7715504cf7eafb","entry":"read_preds","repo":"allenai/ethical-interventions","repo_kind":"official","path":"get_acc.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/get_acc.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":"bf7715504cf7eafb"}},{"code_sha256_prefix":"bf49efe2e2e2a978","entry":"read_squad","repo":"allenai/ethical-interventions","repo_kind":"official","path":"mutils.py","file_url":"https://github.com/allenai/ethical-interventions/blob/HEAD/mutils.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":"bf49efe2e2e2a978"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}