{"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/on-the-noise-robustness-of-in-context","title":"On the Noise Robustness of In-Context Learning for Text Generation","arxiv_id":"2405.17264","date":"2024-05-27","proceeding":null,"authors":["Hongfu Gao","Feipeng Zhang","Wenyu Jiang","Jun Shu","Feng Zheng","Hongxin Wei"],"abstract":"Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the \"noisy\" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking.","url_abs":"https://arxiv.org/abs/2405.17264v3","url_pdf":"https://arxiv.org/pdf/2405.17264v3.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":"on-the-noise-robustness-of-in-context","repo_url":"https://github.com/ml-stat-sustech/local-perplexity-ranking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17264"}},"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":"deterministic:regex_extraction","url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ml-stat-sustech/local-perplexity-ranking","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"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":"29e3b3506f0f02c6","entry":"get_inputes","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/utils.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29e3b3506f0f02c6"}},{"code_sha256_prefix":"792a2c8b12b13057","entry":"get_logger","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/logging.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/logging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"792a2c8b12b13057"}},{"code_sha256_prefix":"14ee44efe36afcfb","entry":"get_prompt_label","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/utils.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14ee44efe36afcfb"}},{"code_sha256_prefix":"4753b3ba80fb1cca","entry":"ignore_pad_dict","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/collators.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/collators.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4753b3ba80fb1cca"}},{"code_sha256_prefix":"aa66004e48501c30","entry":"is_api_available","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/api.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/api.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa66004e48501c30"}},{"code_sha256_prefix":"fc0a9b057f213a9a","entry":"api_get_ppl","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/api.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/api.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc0a9b057f213a9a"}},{"code_sha256_prefix":"430c98669fe41c1a","entry":"api_get_tokens","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"common/api.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/common/api.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"430c98669fe41c1a"}},{"code_sha256_prefix":"de0caf0b39aa6452","entry":"get_dataloader","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"dataset/utils.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/dataset/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de0caf0b39aa6452"}},{"code_sha256_prefix":"58927e35b21bb640","entry":"get_model","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58927e35b21bb640"}},{"code_sha256_prefix":"9350b61b9bb071e4","entry":"get_retriever","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"algorithms/utils.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/algorithms/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9350b61b9bb071e4"}},{"code_sha256_prefix":"a9c86da890c793a6","entry":"get_tokenizer","repo":"ml-stat-Sustech/Local-Perplexity-Ranking","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9c86da890c793a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}