{"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/rho-r-reducing-hallucination-in-open-domain","title":"RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding","arxiv_id":"2212.01588","date":"2022-12-03","proceeding":null,"authors":["Ziwei Ji","Zihan Liu","Nayeon Lee","Tiezheng Yu","Bryan Wilie","Min Zeng","Pascale Fung"],"abstract":"Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which greatly hinders their application. The heterogeneity between external knowledge and dialogue context challenges representation learning and source integration, and further contributes to unfaithfulness. To handle this challenge and generate more faithful responses, this paper presents RHO ($\\rho$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG). We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism. In addition, we devise a response re-ranking technique based on walks over KG sub-graphs for better conversational reasoning. Experimental results on OpenDialKG show that our approach significantly outperforms state-of-the-art methods on both automatic and human evaluation by a large margin, especially in hallucination reduction (17.54% in FeQA).","url_abs":"https://arxiv.org/abs/2212.01588v2","url_pdf":"https://arxiv.org/pdf/2212.01588v2.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":"rho-r-reducing-hallucination-in-open-domain","repo_url":"https://github.com/ziweiji/rho","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2212.01588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.01588"}},"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/ziweiji/rho","reach":null}],"summary":{"ran_fixture":2,"ran_honours":2},"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":4,"samples":[{"code_sha256_prefix":"dac58534a9991421","entry":"calculate_metrics","repo":"ziweiji/rho","repo_kind":"official","path":"kg-cruse_/codes/KGCruse/predict.py","file_url":"https://github.com/ziweiji/rho/blob/HEAD/kg-cruse_/codes/KGCruse/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dac58534a9991421"}},{"code_sha256_prefix":"7563c7670348e8b0","entry":"filter_paths","repo":"ziweiji/rho","repo_kind":"official","path":"kg-cruse_/codes/KGCruse/predict.py","file_url":"https://github.com/ziweiji/rho/blob/HEAD/kg-cruse_/codes/KGCruse/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7563c7670348e8b0"}},{"code_sha256_prefix":"55546fca464d8bf7","entry":"postprocess_output","repo":"ziweiji/rho","repo_kind":"official","path":"src/generation.py","file_url":"https://github.com/ziweiji/rho/blob/HEAD/src/generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55546fca464d8bf7"}},{"code_sha256_prefix":"1bf6a07709288fb4","entry":"remove_incorrect_paths","repo":"ziweiji/rho","repo_kind":"official","path":"kg-cruse_/codes/KGCruse/predict.py","file_url":"https://github.com/ziweiji/rho/blob/HEAD/kg-cruse_/codes/KGCruse/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1bf6a07709288fb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}