{"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/how-should-pre-trained-language-models-be-1","title":"How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?","arxiv_id":"2112.11668","date":"2021-12-22","proceeding":"NeurIPS 2021 12","authors":["Xinhsuai Dong","Luu Anh Tuan","Min Lin","Shuicheng Yan","Hanwang Zhang"],"abstract":"The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment analysis model. In this paper, we demonstrate that adversarial training, the prevalent defense technique, does not directly fit a conventional fine-tuning scenario, because it suffers severely from catastrophic forgetting: failing to retain the generic and robust linguistic features that have already been captured by the pre-trained model. In this light, we propose Robust Informative Fine-Tuning (RIFT), a novel adversarial fine-tuning method from an information-theoretical perspective. In particular, RIFT encourages an objective model to retain the features learned from the pre-trained model throughout the entire fine-tuning process, whereas a conventional one only uses the pre-trained weights for initialization. Experimental results show that RIFT consistently outperforms the state-of-the-arts on two popular NLP tasks: sentiment analysis and natural language inference, under different attacks across various pre-trained language models.","url_abs":"https://arxiv.org/abs/2112.11668v1","url_pdf":"https://arxiv.org/pdf/2112.11668v1.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":"how-should-pre-trained-language-models-be-1","repo_url":"https://github.com/dongxinshuai/rift-neurips2021","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.11668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.11668"}},"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/dongxinshuai/rift-neurips2021","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"dbd26660a4091261","entry":"BertModel_modified","repo":"dongxinshuai/rift-neurips2021","repo_kind":"official","path":"models/AdvPLM.py","file_url":"https://github.com/dongxinshuai/rift-neurips2021/blob/HEAD/models/AdvPLM.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":"dbd26660a4091261"}},{"code_sha256_prefix":"e28ff0b2d17c023d","entry":"MixoutWrapper","repo":"dongxinshuai/rift-neurips2021","repo_kind":"official","path":"models/AdvPLM.py","file_url":"https://github.com/dongxinshuai/rift-neurips2021/blob/HEAD/models/AdvPLM.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e28ff0b2d17c023d"}},{"code_sha256_prefix":"446f071e2676b3c7","entry":"AdvPLM","repo":"dongxinshuai/rift-neurips2021","repo_kind":"official","path":"models/AdvPLM.py","file_url":"https://github.com/dongxinshuai/rift-neurips2021/blob/HEAD/models/AdvPLM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"446f071e2676b3c7"}},{"code_sha256_prefix":"bf19b97fce460555","entry":"RobertaModel_modified","repo":"dongxinshuai/rift-neurips2021","repo_kind":"official","path":"models/AdvPLM.py","file_url":"https://github.com/dongxinshuai/rift-neurips2021/blob/HEAD/models/AdvPLM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf19b97fce460555"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}