{"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/local-explanation-of-dialogue-response","title":"Local Explanation of Dialogue Response Generation","arxiv_id":"2106.06528","date":"2021-06-11","proceeding":"NeurIPS 2021 12","authors":["Yi-Lin Tuan","Connor Pryor","Wenhu Chen","Lise Getoor","William Yang Wang"],"abstract":"In comparison to the interpretation of classification models, the explanation of sequence generation models is also an important problem, however it has seen little attention. In this work, we study model-agnostic explanations of a representative text generation task -- dialogue response generation. Dialog response generation is challenging with its open-ended sentences and multiple acceptable responses. To gain insights into the reasoning process of a generation model, we propose a new method, local explanation of response generation (LERG) that regards the explanations as the mutual interaction of segments in input and output sentences. LERG views the sequence prediction as uncertainty estimation of a human response and then creates explanations by perturbing the input and calculating the certainty change over the human response. We show that LERG adheres to desired properties of explanations for text generation including unbiased approximation, consistency and cause identification. Empirically, our results show that our method consistently improves other widely used methods on proposed automatic- and human- evaluation metrics for this new task by 4.4-12.8%. Our analysis demonstrates that LERG can extract both explicit and implicit relations between input and output segments.","url_abs":"https://arxiv.org/abs/2106.06528v2","url_pdf":"https://arxiv.org/pdf/2106.06528v2.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":"local-explanation-of-dialogue-response","repo_url":"https://github.com/Pascalson/LERG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"implicit-relations","task_name":"Implicit Relations"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.06528","atlas_url":"https://app.syntology.ai/?focus=2106.06528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06528"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/Pascalson/LERG","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"68455dbef5068171","entry":"Explainer","repo":"Pascalson/LERG","repo_kind":"official","path":"lerg/RG_explainers.py","file_url":"https://github.com/Pascalson/LERG/blob/HEAD/lerg/RG_explainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68455dbef5068171"}},{"code_sha256_prefix":"70fb3eef217f4a78","entry":"LERG","repo":"Pascalson/LERG","repo_kind":"official","path":"lerg/RG_explainers.py","file_url":"https://github.com/Pascalson/LERG/blob/HEAD/lerg/RG_explainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70fb3eef217f4a78"}},{"code_sha256_prefix":"bcb189b853348670","entry":"LERG_LIME","repo":"Pascalson/LERG","repo_kind":"official","path":"lerg/RG_explainers.py","file_url":"https://github.com/Pascalson/LERG/blob/HEAD/lerg/RG_explainers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcb189b853348670"}},{"code_sha256_prefix":"ecae1402d47b469a","entry":"read_data","repo":"Pascalson/LERG","repo_kind":"official","path":"explain.py","file_url":"https://github.com/Pascalson/LERG/blob/HEAD/explain.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ecae1402d47b469a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}