{"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/lingoqa-video-question-answering-for","title":"LingoQA: Visual Question Answering for Autonomous Driving","arxiv_id":"2312.14115","date":"2023-12-21","proceeding":null,"authors":["Ana-Maria Marcu","Long Chen","Jan Hünermann","Alice Karnsund","Benoit Hanotte","Prajwal Chidananda","Saurabh Nair","Vijay Badrinarayanan","Alex Kendall","Jamie Shotton","Elahe Arani","Oleg Sinavski"],"abstract":"We introduce LingoQA, a novel dataset and benchmark for visual question answering in autonomous driving. The dataset contains 28K unique short video scenarios, and 419K annotations. Evaluating state-of-the-art vision-language models on our benchmark shows that their performance is below human capabilities, with GPT-4V responding truthfully to 59.6% of the questions compared to 96.6% for humans. For evaluation, we propose a truthfulness classifier, called Lingo-Judge, that achieves a 0.95 Spearman correlation coefficient to human evaluations, surpassing existing techniques like METEOR, BLEU, CIDEr, and GPT-4. We establish a baseline vision-language model and run extensive ablation studies to understand its performance. We release our dataset and benchmark as an evaluation platform for vision-language models in autonomous driving.","url_abs":"https://arxiv.org/abs/2312.14115v4","url_pdf":"https://arxiv.org/pdf/2312.14115v4.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":"lingoqa-video-question-answering-for","repo_url":"https://github.com/wayveai/lingoqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"lingoqa-video-question-answering-for","repo_url":"https://github.com/wayveai/driving-with-llms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"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":"gpt-4","method_name":"GPT-4"},{"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=2312.14115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14115"}},"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/wayveai/lingoqa","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wayveai/driving-with-llms","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"listed":{"samples":10,"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":"fbe62c89d519350f","entry":"extract_labels","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"train_bc.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/train_bc.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":"fbe62c89d519350f"}},{"code_sha256_prefix":"b804c1be469fe22a","entry":"generate_and_tokenize_prompt","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"utils/training_utils.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/utils/training_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":"b804c1be469fe22a"}},{"code_sha256_prefix":"681d026e603bc44f","entry":"generate_square_subsequent_mask","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"models/transformer.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/models/transformer.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":"681d026e603bc44f"}},{"code_sha256_prefix":"b097f43cc24ff9c1","entry":"ingest_vectors","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"models/vector_lm.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/models/vector_lm.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":"b097f43cc24ff9c1"}},{"code_sha256_prefix":"65eb64ba504896b9","entry":"make_ffn","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"models/transformer.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/models/transformer.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":"65eb64ba504896b9"}},{"code_sha256_prefix":"3778d8c0cabf5212","entry":"speed_mph_from_vehicle_desc","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"utils/vector_utils.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/utils/vector_utils.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":"3778d8c0cabf5212"}},{"code_sha256_prefix":"cc1b80d858d4d77c","entry":"traveling_angle_deg_from_vehicle_desc","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"utils/vector_utils.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/utils/vector_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":"cc1b80d858d4d77c"}},{"code_sha256_prefix":"980aeb7dc36e03b3","entry":"xy_from_vehicle_desc","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"utils/vector_utils.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/utils/vector_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":"980aeb7dc36e03b3"}},{"code_sha256_prefix":"c097c27f97405a4a","entry":"load_llama_tokenizer","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"utils/model_utils.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c097c27f97405a4a"}},{"code_sha256_prefix":"d40988c24ba3eaf9","entry":"plain_attention","repo":"wayveai/driving-with-llms","repo_kind":"listed","path":"models/transformer.py","file_url":"https://github.com/wayveai/driving-with-llms/blob/HEAD/models/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d40988c24ba3eaf9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}