{"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/enhancing-noise-robustness-of-retrieval","title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","arxiv_id":"2405.20978","date":"2024-05-31","proceeding":null,"authors":["Feiteng Fang","Yuelin Bai","Shiwen Ni","Min Yang","Xiaojun Chen","Ruifeng Xu"],"abstract":"Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges. However, inappropriate retrieved passages can potentially hinder the LLMs' capacity to generate comprehensive and high-quality responses. Prior RAG studies on the robustness of retrieval noises often confine themselves to a limited set of noise types, deviating from real-world retrieval environments and limiting practical applicability. In this study, we initially investigate retrieval noises and categorize them into three distinct types, reflecting real-world environments. We analyze the impact of these various retrieval noises on the robustness of LLMs. Subsequently, we propose a novel RAG approach known as Retrieval-augmented Adaptive Adversarial Training (RAAT). RAAT leverages adaptive adversarial training to dynamically adjust the model's training process in response to retrieval noises. Concurrently, it employs multi-task learning to ensure the model's capacity to internally recognize noisy contexts. Extensive experiments demonstrate that the LLaMA-2 7B model trained using RAAT exhibits significant improvements in F1 and EM scores under diverse noise conditions. For reproducibility, we release our code and data at: https://github.com/calubkk/RAAT.","url_abs":"https://arxiv.org/abs/2405.20978v1","url_pdf":"https://arxiv.org/pdf/2405.20978v1.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":"enhancing-noise-robustness-of-retrieval","repo_url":"https://github.com/calubkk/raat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.20978","atlas_url":"https://app.syntology.ai/?focus=2405.20978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20978"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/calubkk/raat","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/calubkk/RAAT","reach":{"status":"ok"}}],"summary":{"ran":9},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"0e88ab2d4fdaca3c","entry":"exact_match_score","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/metrics/em_f1.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/metrics/em_f1.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":"0e88ab2d4fdaca3c"}},{"code_sha256_prefix":"fa90936b1f466162","entry":"extract_answer","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/utils/answer_processor.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/utils/answer_processor.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":"fa90936b1f466162"}},{"code_sha256_prefix":"a38180bf25a2409b","entry":"f1_score","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/metrics/em_f1.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/metrics/em_f1.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":"a38180bf25a2409b"}},{"code_sha256_prefix":"971d489a6cc144e2","entry":"generate_answer_wo_retrieval","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/utils/answer_processor.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/utils/answer_processor.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":"971d489a6cc144e2"}},{"code_sha256_prefix":"a774a791d4dee82a","entry":"load_data","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/utils/loader.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/utils/loader.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":"a774a791d4dee82a"}},{"code_sha256_prefix":"5bfb8eaceb8fc0c1","entry":"normalize_answer","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/metrics/em_f1.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/metrics/em_f1.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":"5bfb8eaceb8fc0c1"}},{"code_sha256_prefix":"ce5b6f1069f30c8c","entry":"rerank_ctx","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/utils/select_retrieve.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/utils/select_retrieve.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":"ce5b6f1069f30c8c"}},{"code_sha256_prefix":"30ba762e411ca569","entry":"rerank_two_ctx","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/utils/select_retrieve.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/utils/select_retrieve.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":"30ba762e411ca569"}},{"code_sha256_prefix":"24854ea4182bf3fc","entry":"schedule_ctx","repo":"calubkk/RAAT","repo_kind":"official","path":"tuner/utils/select_retrieve.py","file_url":"https://github.com/calubkk/RAAT/blob/HEAD/tuner/utils/select_retrieve.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":"24854ea4182bf3fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}