{"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/learning-to-ask-informative-questions","title":"Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain","arxiv_id":"2406.17453","date":"2024-06-25","proceeding":null,"authors":["Davide Mazzaccara","Alberto Testoni","Raffaella Bernardi"],"abstract":"Questions are essential tools for acquiring the necessary information to complete information-seeking tasks. However, large language models (LLMs), especially open-source models, often perform poorly in generating informative questions, as measured by expected information gain (EIG). In this paper, we propose a method to enhance the informativeness of LLM-generated questions in 20-question game dialogues. We sample multiple questions from the same model (LLAMA 2-CHAT 7B) for each game and create pairs of low-EIG and high-EIG questions to apply a Direct Preference Optimization (DPO) algorithm. Our results show that this method produces more effective questions (in terms of EIG), even in domains different from those used to train the DPO model.","url_abs":"https://arxiv.org/abs/2406.17453v3","url_pdf":"https://arxiv.org/pdf/2406.17453v3.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":"learning-to-ask-informative-questions","repo_url":"https://github.com/dmazzaccara/learningtoask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"informativeness","task_name":"Informativeness"}],"methods":[{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.17453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17453"}},"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/dmazzaccara/learningtoask","reach":null}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"3fddf7fd0787a1de","entry":"apply_chat","repo":"dmazzaccara/learningtoask","repo_kind":"official","path":"scripts/SFT.py","file_url":"https://github.com/dmazzaccara/learningtoask/blob/HEAD/scripts/SFT.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3fddf7fd0787a1de"}},{"code_sha256_prefix":"176c85c2b4299464","entry":"get_lists_of_candidates","repo":"dmazzaccara/learningtoask","repo_kind":"official","path":"scripts/bootstrapping.py","file_url":"https://github.com/dmazzaccara/learningtoask/blob/HEAD/scripts/bootstrapping.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"176c85c2b4299464"}},{"code_sha256_prefix":"bb9eb71c47112a04","entry":"llama2_model_call","repo":"dmazzaccara/learningtoask","repo_kind":"official","path":"scripts/bootstrapping.py","file_url":"https://github.com/dmazzaccara/learningtoask/blob/HEAD/scripts/bootstrapping.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb9eb71c47112a04"}},{"code_sha256_prefix":"dc9dd95aae3f7dd6","entry":"padding_token","repo":"dmazzaccara/learningtoask","repo_kind":"official","path":"scripts/DPO.py","file_url":"https://github.com/dmazzaccara/learningtoask/blob/HEAD/scripts/DPO.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc9dd95aae3f7dd6"}},{"code_sha256_prefix":"b598c946805ec74e","entry":"repetitive_words_collector","repo":"dmazzaccara/learningtoask","repo_kind":"official","path":"scripts/bootstrapping.py","file_url":"https://github.com/dmazzaccara/learningtoask/blob/HEAD/scripts/bootstrapping.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b598c946805ec74e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}