{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deepedit-knowledge-editing-as-decoding-with","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","arxiv_id":"2401.10471","date":"2024-01-19","proceeding":null,"authors":["Yiwei Wang","Muhao Chen","Nanyun Peng","Kai-Wei Chang"],"abstract":"How to edit the knowledge in multi-step reasoning has become the major challenge in the knowledge editing (KE) of large language models (LLMs). The difficulty arises because the hallucinations of LLMs during multi-step reasoning often lead to incorrect use of new knowledge and incorrect answers. To address this issue, we design decoding constraints to \"regulate\" LLMs' reasoning, enhancing logical coherence when incorporating new knowledge. We propose a new KE framework: DEEPEDIT (Depth-first Search-based Constrained Decoding for Knowledge Editing), which enhances LLMs's ability to generate coherent reasoning chains with new knowledge through depth-first search. Our search selects the most important knowledge that satisfies our constraints as the reasoning step to efficiently increase the reasoning depth. In addition to DEEPEDIT, we propose two new KE benchmarks: MQUAKE-2002 and MQUAKE-HARD, which provide more precise and challenging assessments of KE approaches. Qualitatively, DEEPEDIT enables LLMs to produce succinct and coherent reasoning chains involving new knowledge. Quantitatively, it yields significant improvements on multiple KE benchmarks.","url_abs":"https://arxiv.org/abs/2401.10471v5","url_pdf":"https://arxiv.org/pdf/2401.10471v5.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":"deepedit-knowledge-editing-as-decoding-with","repo_url":"https://github.com/wangywust/deepedit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deepedit-knowledge-editing-as-decoding-with","repo_url":"https://github.com/sycny/rae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"multi-hop-question-answering","task_name":"Multi-hop Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"knowledge-editing","task_name":"knowledge editing"}],"methods":[],"datasets_introduced":[{"slug":"mquake-2002","name":"MQuAKE-2002","full_name":""},{"slug":"mquake-hard","name":"MQuAKE-hard","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.10471","atlas_url":"https://app.syntology.ai/?focus=2401.10471","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2401.10471"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2401.10471\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2401.10471"},"call":"get_concepts_for_paper(arxiv_id=\"2401.10471\")"}],"by_repo":[{"repo":"wangywust/deepedit","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sycny/rae","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.19631"],"harvested_for_calls":[{"arxiv_id":"2403.19631","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.19631"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.19631\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"225009ef0722231678094702742b6861dbbe824f3978469fb7f91e8a1c517f3d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}