{"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/found-in-the-middle-permutation-self","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","arxiv_id":"2310.07712","date":"2023-10-11","proceeding":null,"authors":["Raphael Tang","Xinyu Zhang","Xueguang Ma","Jimmy Lin","Ferhan Ture"],"abstract":"Large language models (LLMs) exhibit positional bias in how they use context, which especially complicates listwise ranking. To address this, we propose permutation self-consistency, a form of self-consistency over ranking list outputs of black-box LLMs. Our key idea is to marginalize out different list orders in the prompt to produce an order-independent ranking with less positional bias. First, given some input prompt, we repeatedly shuffle the list in the prompt and pass it through the LLM while holding the instructions the same. Next, we aggregate the resulting sample of rankings by computing the central ranking closest in distance to all of them, marginalizing out prompt order biases in the process. Theoretically, we prove the robustness of our method, showing convergence to the true ranking in the presence of random perturbations. Empirically, on five list-ranking datasets in sorting and passage reranking, our approach improves scores from conventional inference by up to 7-18% for GPT-3.5 and 8-16% for LLaMA v2 (70B), surpassing the previous state of the art in passage reranking. Our code is at https://github.com/castorini/perm-sc.","url_abs":"https://arxiv.org/abs/2310.07712v2","url_pdf":"https://arxiv.org/pdf/2310.07712v2.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":"found-in-the-middle-permutation-self","repo_url":"https://github.com/castorini/perm-sc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"Passage Reranking"},{"task_slug":"reranking","task_name":"Reranking"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.07712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07712"}},"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/castorini/perm-sc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"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":"f28780b2b6c02e7e","entry":"cdk_graph_distance","repo":"castorini/perm-sc","repo_kind":"official","path":"permsc/aggregator/utils.py","file_url":"https://github.com/castorini/perm-sc/blob/HEAD/permsc/aggregator/utils.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":"f28780b2b6c02e7e"}},{"code_sha256_prefix":"f8155d2e301008e8","entry":"cdk_graph_from_preferences","repo":"castorini/perm-sc","repo_kind":"official","path":"permsc/aggregator/utils.py","file_url":"https://github.com/castorini/perm-sc/blob/HEAD/permsc/aggregator/utils.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":"f8155d2e301008e8"}},{"code_sha256_prefix":"0a4bd4c0a5de22dc","entry":"max_tokens","repo":"castorini/perm-sc","repo_kind":"official","path":"permsc/llm/utils.py","file_url":"https://github.com/castorini/perm-sc/blob/HEAD/permsc/llm/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a4bd4c0a5de22dc"}},{"code_sha256_prefix":"eea83f13a4cc4b1f","entry":"maybe_list_to_list","repo":"castorini/perm-sc","repo_kind":"official","path":"permsc/types.py","file_url":"https://github.com/castorini/perm-sc/blob/HEAD/permsc/types.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":"eea83f13a4cc4b1f"}},{"code_sha256_prefix":"be348524e1f1ae6a","entry":"preferences_from_cdk_graph","repo":"castorini/perm-sc","repo_kind":"official","path":"permsc/aggregator/utils.py","file_url":"https://github.com/castorini/perm-sc/blob/HEAD/permsc/aggregator/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be348524e1f1ae6a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}