{"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/self-reflection-outcome-is-sensitive-to","title":"Self-Reflection Outcome is Sensitive to Prompt Construction","arxiv_id":"2406.10400","date":"2024-06-14","proceeding":null,"authors":["Fengyuan Liu","Nouar AlDahoul","Gregory Eady","Yasir Zaki","Bedoor AlShebli","Talal Rahwan"],"abstract":"Large language models (LLMs) demonstrate impressive zero-shot and few-shot reasoning capabilities. Some propose that such capabilities can be improved through self-reflection, i.e., letting LLMs reflect on their own output to identify and correct mistakes in the initial responses. However, despite some evidence showing the benefits of self-reflection, recent studies offer mixed results. Here, we aim to reconcile these conflicting findings by first demonstrating that the outcome of self-reflection is sensitive to prompt wording; e.g., LLMs are more likely to conclude that it has made a mistake when explicitly prompted to find mistakes. Consequently, idiosyncrasies in reflection prompts may lead LLMs to change correct responses unnecessarily. We show that most prompts used in the self-reflection literature are prone to this bias. We then propose different ways of constructing prompts that are conservative in identifying mistakes and show that self-reflection using such prompts results in higher accuracy. Our findings highlight the importance of prompt engineering in self-reflection tasks. We release our code at https://github.com/Michael98Liu/mixture-of-prompts.","url_abs":"https://arxiv.org/abs/2406.10400v1","url_pdf":"https://arxiv.org/pdf/2406.10400v1.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":"self-reflection-outcome-is-sensitive-to","repo_url":"https://github.com/michael98liu/mixture-of-prompts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10400"}},"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/michael98liu/mixture-of-prompts","reach":{"status":"ok"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"fb55088ee424863e","entry":"arrayGenerate","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"promptarray/generate.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/promptarray/generate.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":"fb55088ee424863e"}},{"code_sha256_prefix":"3c4caa822ad9ac6b","entry":"convertData","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"MoP/experiment.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/MoP/experiment.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":"3c4caa822ad9ac6b"}},{"code_sha256_prefix":"96e8ebef5ac6e213","entry":"convertRow","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"MoP/experiment.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/MoP/experiment.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":"96e8ebef5ac6e213"}},{"code_sha256_prefix":"801e6e5af2826782","entry":"loadCSQA","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"MoP/dataloader.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/MoP/dataloader.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":"801e6e5af2826782"}},{"code_sha256_prefix":"c281971d33901661","entry":"loadGSM8k","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"MoP/dataloader.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/MoP/dataloader.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":"c281971d33901661"}},{"code_sha256_prefix":"98df12aef4feea81","entry":"loadIdeology","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"MoP/dataloader.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/MoP/dataloader.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":"98df12aef4feea81"}},{"code_sha256_prefix":"edf765ec3dc04f6d","entry":"splitExampleTrainTest","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"MoP/experiment.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/MoP/experiment.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":"edf765ec3dc04f6d"}},{"code_sha256_prefix":"ff8db6af57706115","entry":"split_last_sentence","repo":"michael98liu/mixture-of-prompts","repo_kind":"official","path":"promptarray/lambada_score.py","file_url":"https://github.com/michael98liu/mixture-of-prompts/blob/HEAD/promptarray/lambada_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff8db6af57706115"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}