{"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/ask-an-expert-leveraging-language-models-to","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","arxiv_id":"2305.17878","date":"2023-05-29","proceeding":null,"authors":["Qiang Zhang","Jason Naradowsky","Yusuke Miyao"],"abstract":"Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the \"Ask an Expert\" framework in which the model is trained with access to an \"expert\" which it can consult at each turn. Advice is solicited via a structured dialogue with the expert, and the model is optimized to selectively utilize (or ignore) it given the context and dialogue history. In this work the expert takes the form of an LLM. We evaluate this framework in a mental health support domain, where the structure of the expert conversation is outlined by pre-specified prompts which reflect a reasoning strategy taught to practitioners in the field. Blenderbot models utilizing \"Ask an Expert\" show quality improvements across all expert sizes, including those with fewer parameters than the dialogue model itself. Our best model provides a $\\sim 10\\%$ improvement over baselines, approaching human-level scores on \"engingingness\" and \"helpfulness\" metrics.","url_abs":"https://arxiv.org/abs/2305.17878v1","url_pdf":"https://arxiv.org/pdf/2305.17878v1.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":"ask-an-expert-leveraging-language-models-to","repo_url":"https://github.com/qzx7/bbmhreasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.17878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17878"}},"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/qzx7/bbmhreasoning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"89b3e7275cff69a1","entry":"get_gpt_result","repo":"qzx7/bbmhreasoning","repo_kind":"official","path":"bbmhr/pipeline/prompting.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/pipeline/prompting.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":"89b3e7275cff69a1"}},{"code_sha256_prefix":"4dc28061461f4485","entry":"load_openers_from_file","repo":"qzx7/bbmhreasoning","repo_kind":"official","path":"bbmhr/parlai/tasks/self_chat/worlds.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/parlai/tasks/self_chat/worlds.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":"4dc28061461f4485"}},{"code_sha256_prefix":"88508a5475fdac30","entry":"post_process_annotation","repo":"qzx7/bbmhreasoning","repo_kind":"official","path":"bbmhr/pipeline/joint_learning.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/pipeline/joint_learning.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":"88508a5475fdac30"}},{"code_sha256_prefix":"fa46e509a592d9d6","entry":"read_batch_data","repo":"qzx7/bbmhreasoning","repo_kind":"official","path":"bbmhr/pipeline/joint_learning.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/pipeline/joint_learning.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":"fa46e509a592d9d6"}},{"code_sha256_prefix":"2065e1a55aa14adf","entry":"read_prompt","repo":"qzx7/bbmhreasoning","repo_kind":"official","path":"bbmhr/pipeline/prompting.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/pipeline/prompting.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":"2065e1a55aa14adf"}},{"code_sha256_prefix":"14de46d80233861c","entry":"reformat_source_data","repo":"qzx7/bbmhreasoning","repo_kind":"official","path":"bbmhr/pipeline/prompting.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/pipeline/prompting.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":"14de46d80233861c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}