{"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/instructed-language-models-with-retrievers","title":"Instructed Language Models with Retrievers Are Powerful Entity Linkers","arxiv_id":"2311.03250","date":"2023-11-06","proceeding":null,"authors":["Zilin Xiao","Ming Gong","Jie Wu","Xingyao Zhang","Linjun Shou","Jian Pei","Daxin Jiang"],"abstract":"Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer from hallucinations, thus unsuitable for entity-centric tasks like entity linking (EL) requiring precise entity predictions over a large knowledge base. We present Instructed Generative Entity Linker (INSGENEL), the first approach that enables casual language models to perform entity linking over knowledge bases. Several methods to equip language models with EL capability were proposed in this work, including (i) a sequence-to-sequence training EL objective with instruction-tuning, (ii) a novel generative EL framework based on a light-weight potential mention retriever that frees the model from heavy and non-parallelizable decoding, achieving 4$\\times$ speedup without compromise on linking metrics. INSGENEL outperforms previous generative alternatives with +6.8 F1 points gain on average, also with a huge advantage in training data efficiency and training compute consumption. In addition, our skillfully engineered in-context learning (ICL) framework for EL still lags behind INSGENEL significantly, reaffirming that the EL task remains a persistent hurdle for general LLMs.","url_abs":"https://arxiv.org/abs/2311.03250v1","url_pdf":"https://arxiv.org/pdf/2311.03250v1.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":"instructed-language-models-with-retrievers","repo_url":"https://github.com/mrzilinxiao/insgenentitylinking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.03250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03250"}},"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/mrzilinxiao/insgenentitylinking","reach":{"status":"ok"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":10,"samples":[{"code_sha256_prefix":"0fb666de4b9f43cd","entry":"add_space_before_punctuation","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"eval/universal_offline_eval.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/eval/universal_offline_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0fb666de4b9f43cd"}},{"code_sha256_prefix":"64a6f1289fc8dab9","entry":"create_label_json","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"eval/universal_offline_eval.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/eval/universal_offline_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"64a6f1289fc8dab9"}},{"code_sha256_prefix":"cee2bbc2f9b14403","entry":"has_non_english_chars","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"data_scripts/build_model_trie.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/data_scripts/build_model_trie.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cee2bbc2f9b14403"}},{"code_sha256_prefix":"f25b1071462e07b3","entry":"has_non_english_chars","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"data_scripts/create_candidates_dict.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/data_scripts/create_candidates_dict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f25b1071462e07b3"}},{"code_sha256_prefix":"6ebe9fdfdb23a57a","entry":"hex2int","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"data_scripts/create_candidates_dict.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/data_scripts/create_candidates_dict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ebe9fdfdb23a57a"}},{"code_sha256_prefix":"2bbccdf20450b081","entry":"llama_get_entity_spans_to_elevant_format","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"eval/universal_offline_eval.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/eval/universal_offline_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bbccdf20450b081"}},{"code_sha256_prefix":"8ea3c73453786f73","entry":"preprocess_text","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"data_scripts/wiki_dump.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/data_scripts/wiki_dump.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ea3c73453786f73"}},{"code_sha256_prefix":"651f2f036c814d5c","entry":"replace_unicode","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"data_scripts/create_candidates_dict.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/data_scripts/create_candidates_dict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"651f2f036c814d5c"}},{"code_sha256_prefix":"5d1af3b21d7c337e","entry":"split_by_punc_fn","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"src/common_utils/split.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/src/common_utils/split.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5d1af3b21d7c337e"}},{"code_sha256_prefix":"055674fc00478970","entry":"split_sentence","repo":"mrzilinxiao/insgenentitylinking","repo_kind":"official","path":"src/common_utils/split.py","file_url":"https://github.com/mrzilinxiao/insgenentitylinking/blob/HEAD/src/common_utils/split.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":"055674fc00478970"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}