{"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-easily-do-irrelevant-inputs-skew-the","title":"How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?","arxiv_id":"2404.03302","date":"2024-04-04","proceeding":null,"authors":["Siye Wu","Jian Xie","Jiangjie Chen","Tinghui Zhu","Kai Zhang","Yanghua Xiao"],"abstract":"By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current retrieval systems, there might exist irrelevant information within those retrieving top-ranked passages. In this work, we present a comprehensive investigation into the robustness of LLMs to different types of irrelevant information under various conditions. We initially introduce a framework to construct high-quality irrelevant information that ranges from semantically unrelated, partially related, and related to questions. Furthermore, our analysis demonstrates that the constructed irrelevant information not only scores highly on similarity metrics, being highly retrieved by existing systems, but also bears semantic connections to the context. Our investigation reveals that current LLMs still face challenges in discriminating highly semantically related information and can be easily distracted by these irrelevant yet misleading content. Besides, we also find that current solutions for handling irrelevant information have limitations in improving the robustness of LLMs to such distractions. All the resources are available on GitHub at https://github.com/Di-viner/LLM-Robustness-to-Irrelevant-Information.","url_abs":"https://arxiv.org/abs/2404.03302v4","url_pdf":"https://arxiv.org/pdf/2404.03302v4.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-easily-do-irrelevant-inputs-skew-the","repo_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.03302","atlas_url":"https://app.syntology.ai/?focus=2404.03302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03302"}},"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/di-viner/llm-robustness-to-irrelevant-information","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"90477c43da0ab5d1","entry":"build_multiple_choice_quantity_prompt","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"prompt_preparation.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/prompt_preparation.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":"90477c43da0ab5d1"}},{"code_sha256_prefix":"84badbefbdc7ff60","entry":"build_multiple_choice_semantic_relevance_prompt","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"prompt_preparation.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/prompt_preparation.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":"84badbefbdc7ff60"}},{"code_sha256_prefix":"3d3918e09b5366dd","entry":"calc_cost_w_tokens","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"openai_request.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/openai_request.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":"3d3918e09b5366dd"}},{"code_sha256_prefix":"287dc9d3368dc058","entry":"create_dict_id_to_data","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"utils.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/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":"287dc9d3368dc058"}},{"code_sha256_prefix":"15be9688c6f6663f","entry":"get_dataset_prefix_and_path","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"utils.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/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":"15be9688c6f6663f"}},{"code_sha256_prefix":"f5009f2a6258e5e8","entry":"limited_execution_time","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"openai_request.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/openai_request.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":"f5009f2a6258e5e8"}},{"code_sha256_prefix":"959eef29433a0a23","entry":"load_line_json_data","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"utils.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"959eef29433a0a23"}},{"code_sha256_prefix":"d3c8b3cc8cb6d337","entry":"openai_unit_price","repo":"di-viner/llm-robustness-to-irrelevant-information","repo_kind":"official","path":"openai_request.py","file_url":"https://github.com/di-viner/llm-robustness-to-irrelevant-information/blob/HEAD/openai_request.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3c8b3cc8cb6d337"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}