{"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/vibecheck-discover-and-quantify-qualitative","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","arxiv_id":"2410.12851","date":"2024-10-10","proceeding":null,"authors":["Lisa Dunlap","Krishna Mandal","Trevor Darrell","Jacob Steinhardt","Joseph E Gonzalez"],"abstract":"Large language models (LLMs) often exhibit subtle yet distinctive characteristics in their outputs that users intuitively recognize, but struggle to quantify. These \"vibes\" -- such as tone, formatting, or writing style -- influence user preferences, yet traditional evaluations focus primarily on the singular axis of correctness. We introduce VibeCheck, a system for automatically comparing a pair of LLMs by discovering identifying traits of a model (vibes) that are well-defined, differentiating, and user-aligned. VibeCheck iteratively discovers vibes from model outputs and then utilizes a panel of LLM judges to quantitatively measure the utility of each vibe. We validate that the vibes generated by VibeCheck align with those found in human discovery and run VibeCheck on pairwise preference data from real-world user conversations with Llama-3-70b vs GPT-4. VibeCheck reveals that Llama has a friendly, funny, and somewhat controversial vibe. These vibes predict model identity with 80% accuracy and human preference with 61% accuracy. Lastly, we run VibeCheck on a variety of models and tasks including summarization, math, and captioning to provide insight into differences in model behavior. VibeCheck discovers vibes like Command X prefers to add concrete intros and conclusions when summarizing in comparison to TNGL, Llama-405b often overexplains its thought process on math problems compared to GPT-4o, and GPT-4 prefers to focus on the mood and emotions of the scene when captioning compared to Gemini-1.5-Flash. Code and vibe visualizer found at https://bench-mark.org/","url_abs":"https://arxiv.org/abs/2410.12851v7","url_pdf":"https://arxiv.org/pdf/2410.12851v7.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":"vibecheck-discover-and-quantify-qualitative","repo_url":"https://github.com/lisadunlap/vibecheck","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12851"}},"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/lisadunlap/vibecheck","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"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":12,"samples":[{"code_sha256_prefix":"d43d48a977514ab1","entry":"compute_p_values","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"paper_code/components/mm_and_pp_modeling.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/paper_code/components/mm_and_pp_modeling.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":"d43d48a977514ab1"}},{"code_sha256_prefix":"625dda65dfeec554","entry":"convert_scores","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"components/rank.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/components/rank.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":"625dda65dfeec554"}},{"code_sha256_prefix":"9fe570fe6dee5c7d","entry":"extract_scores","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"get_preference_labels.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/get_preference_labels.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":"9fe570fe6dee5c7d"}},{"code_sha256_prefix":"ff52df7cc40b6df3","entry":"get_feature_df","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lisadunlap/vibecheck/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff52df7cc40b6df3"}},{"code_sha256_prefix":"4d9aba8951b2c78e","entry":"get_pref_score","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/utils.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":"4d9aba8951b2c78e"}},{"code_sha256_prefix":"3d2eae234a32c4b6","entry":"hash_key","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"components/utils_general.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/components/utils_general.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":"3d2eae234a32c4b6"}},{"code_sha256_prefix":"44accab68f097031","entry":"parse_bullets","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"components/propose.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/components/propose.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":"44accab68f097031"}},{"code_sha256_prefix":"abe73ae6be6537d7","entry":"prep_feat_df","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"paper_code/components/mm_and_pp_modeling.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/paper_code/components/mm_and_pp_modeling.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":"abe73ae6be6537d7"}},{"code_sha256_prefix":"b7a4a6395d8c9766","entry":"ranker_postprocess_multi","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"components/rank.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/components/rank.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":"b7a4a6395d8c9766"}},{"code_sha256_prefix":"686042408a0ee264","entry":"train_and_evaluate","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"paper_code/components/mm_and_pp_modeling.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/paper_code/components/mm_and_pp_modeling.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":"686042408a0ee264"}},{"code_sha256_prefix":"05b871bc2f057338","entry":"get_text_embedding","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"components/utils_text_embedding.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/components/utils_text_embedding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"05b871bc2f057338"}},{"code_sha256_prefix":"1abaa627e80ee46b","entry":"train_and_evaluate_model","repo":"lisadunlap/vibecheck","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1abaa627e80ee46b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}