{"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/prompt-waywardness-the-curious-case-of","title":"Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts","arxiv_id":"2112.08348","date":"2021-12-15","proceeding":"NAACL 2022 7","authors":["Daniel Khashabi","Shane Lyu","Sewon Min","Lianhui Qin","Kyle Richardson","Sean Welleck","Hannaneh Hajishirzi","Tushar Khot","Ashish Sabharwal","Sameer Singh","Yejin Choi"],"abstract":"Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the feasibility of extracting a discrete (textual) interpretation of continuous prompts that is faithful to the problem they solve. In practice, we observe a \"wayward\" behavior between the task solved by continuous prompts and their nearest neighbor discrete projections: We can find continuous prompts that solve a task while being projected to an arbitrary text (e.g., definition of a different or even a contradictory task), while being within a very small (2%) margin of the best continuous prompt of the same size for the task. We provide intuitions behind this odd and surprising behavior, as well as extensive empirical analyses quantifying the effect of various parameters. For instance, for larger model sizes we observe higher waywardness, i.e, we can find prompts that more closely map to any arbitrary text with a smaller drop in accuracy. These findings have important implications relating to the difficulty of faithfully interpreting continuous prompts and their generalization across models and tasks, providing guidance for future progress in prompting language models.","url_abs":"https://arxiv.org/abs/2112.08348v2","url_pdf":"https://arxiv.org/pdf/2112.08348v2.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":"prompt-waywardness-the-curious-case-of","repo_url":"https://github.com/alrope123/prompt-waywardness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.08348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08348"}},"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/alrope123/prompt-waywardness","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"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":"126ae8eeb63d59bf","entry":"get_label","repo":"alrope123/prompt-waywardness","repo_kind":"official","path":"generate_k_shot_data.py","file_url":"https://github.com/alrope123/prompt-waywardness/blob/HEAD/generate_k_shot_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"126ae8eeb63d59bf"}},{"code_sha256_prefix":"c5c4435a7bbecdc7","entry":"load_datasets","repo":"alrope123/prompt-waywardness","repo_kind":"official","path":"generate_k_shot_data.py","file_url":"https://github.com/alrope123/prompt-waywardness/blob/HEAD/generate_k_shot_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c5c4435a7bbecdc7"}},{"code_sha256_prefix":"efd1b7718b950470","entry":"split_header","repo":"alrope123/prompt-waywardness","repo_kind":"official","path":"generate_k_shot_data.py","file_url":"https://github.com/alrope123/prompt-waywardness/blob/HEAD/generate_k_shot_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efd1b7718b950470"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}