{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/question-answering/papers/14","list_of":"/task/question-answering","task":"Question Answering","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":14,"pages_in_order":109,"rows_per_page":100,"rows":[1301,1400],"of":10817,"counts":{"archive_papers_tagged":10817,"with_a_code_link":4171,"where_syntology_ran_a_sample":1274,"not_listed_spam_title":0,"listed":10817,"listed_where_code_ran":1274,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1073,"every_run_a_failure_of_syntologys_instrument":201,"listed_with_a_run_with_no_instrument_failure":1073,"listed_every_run_a_failure_of_syntologys_instrument":201,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/question-answering","prev":"/task/question-answering/papers/13","next":"/task/question-answering/papers/15","papers":[{"url":"/paper/voxelprompt-a-vision-language-agent-for","slug":"voxelprompt-a-vision-language-agent-for","title":"VoxelPrompt: A Vision-Language Agent for Grounded Medical Image Analysis","date":"2024-10-10","arxiv_id":"2410.08397","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/voxelprompt-a-vision-language-agent-for#ran","syntology_url":"https://syntology.ai/paper/2410.08397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08397"}},"official":{"repos":["dalcalab/voxel"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/auditwen-an-open-source-large-language-model","slug":"auditwen-an-open-source-large-language-model","title":"AuditWen:An Open-Source Large Language Model for Audit","date":"2024-10-09","arxiv_id":"2410.10873","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-readiness-of-prominent-small","slug":"exploring-the-readiness-of-prominent-small","title":"Exploring the Readiness of Prominent Small Language Models for the Democratization of Financial Literacy","date":"2024-10-09","arxiv_id":"2410.07118","repositories_listed":1,"syntology":null},{"url":"/paper/sparsegrad-a-selective-method-for-efficient","slug":"sparsegrad-a-selective-method-for-efficient","title":"SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers","date":"2024-10-09","arxiv_id":"2410.07383","repositories_listed":1,"syntology":null},{"url":"/paper/utilize-the-flow-before-stepping-into-the","slug":"utilize-the-flow-before-stepping-into-the","title":"Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning","date":"2024-10-09","arxiv_id":"2410.06913","repositories_listed":1,"syntology":null},{"url":"/paper/weak-eval-strong-evaluating-and-eliciting","slug":"weak-eval-strong-evaluating-and-eliciting","title":"Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles","date":"2024-10-09","arxiv_id":"2410.06733","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/weak-eval-strong-evaluating-and-eliciting#ran","syntology_url":"https://syntology.ai/paper/2410.06733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06733"}},"official":{"repos":["chenqi008/LateralThinking"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/core-tokensets-for-data-efficient-sequential","slug":"core-tokensets-for-data-efficient-sequential","title":"Core Tokensets for Data-efficient Sequential Training of Transformers","date":"2024-10-08","arxiv_id":"2410.05800","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-sparql-generation-by-triplet-order","slug":"enhancing-sparql-generation-by-triplet-order","title":"Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training","date":"2024-10-08","arxiv_id":"2410.05731","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-temporal-modeling-of-video-llms-via","slug":"enhancing-temporal-modeling-of-video-llms-via","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","date":"2024-10-08","arxiv_id":"2410.05714","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-temporal-modeling-of-video-llms-via#ran","syntology_url":"https://syntology.ai/paper/2410.05714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05714"}},"official":{"repos":["lavi-lab/tg-vid"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ervqa-a-dataset-to-benchmark-the-readiness-of","slug":"ervqa-a-dataset-to-benchmark-the-readiness-of","title":"ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital Environments","date":"2024-10-08","arxiv_id":"2410.06420","repositories_listed":1,"syntology":null},{"url":"/paper/llaca-multimodal-large-language-continual","slug":"llaca-multimodal-large-language-continual","title":"Large Continual Instruction Assistant","date":"2024-10-08","arxiv_id":"2410.10868","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llaca-multimodal-large-language-continual#ran","syntology_url":"https://syntology.ai/paper/2410.10868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10868"}},"official":{"repos":["jingyangqiao/coin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-large-language-models-and-tunings","slug":"multimodal-large-language-models-and-tunings","title":"Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond","date":"2024-10-08","arxiv_id":"2410.05608","repositories_listed":1,"syntology":null},{"url":"/paper/pdf-wukong-a-large-multimodal-model-for","slug":"pdf-wukong-a-large-multimodal-model-for","title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","date":"2024-10-08","arxiv_id":"2410.05970","repositories_listed":1,"syntology":null},{"url":"/paper/teochat-a-large-vision-language-assistant-for","slug":"teochat-a-large-vision-language-assistant-for","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","date":"2024-10-08","arxiv_id":"2410.06234","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/teochat-a-large-vision-language-assistant-for#ran","syntology_url":"https://syntology.ai/paper/2410.06234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06234"}},"official":{"repos":["ermongroup/teochat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/actiview-evaluating-active-perception-ability","slug":"actiview-evaluating-active-perception-ability","title":"ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models","date":"2024-10-07","arxiv_id":"2410.04659","repositories_listed":1,"syntology":null},{"url":"/paper/casimedicos-arg-a-medical-question-answering","slug":"casimedicos-arg-a-medical-question-answering","title":"CasiMedicos-Arg: A Medical Question Answering Dataset Annotated with Explanatory Argumentative Structures","date":"2024-10-07","arxiv_id":"2410.05235","repositories_listed":1,"syntology":null},{"url":"/paper/zebra-zero-shot-example-based-retrieval","slug":"zebra-zero-shot-example-based-retrieval","title":"ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering","date":"2024-10-07","arxiv_id":"2410.05077","repositories_listed":1,"syntology":null},{"url":"/paper/famma-a-benchmark-for-financial-domain","slug":"famma-a-benchmark-for-financial-domain","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","date":"2024-10-06","arxiv_id":"2410.04526","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/famma-a-benchmark-for-financial-domain#ran","syntology_url":"https://syntology.ai/paper/2410.04526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04526"}},"official":{"repos":["famma-bench/bench-script"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mc-cot-a-modular-collaborative-cot-framework","slug":"mc-cot-a-modular-collaborative-cot-framework","title":"MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration","date":"2024-10-06","arxiv_id":"2410.04521","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mc-cot-a-modular-collaborative-cot-framework#ran","syntology_url":"https://syntology.ai/paper/2410.04521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04521"}},"official":{"repos":["thomaswei-cn/MC-CoT"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-ai-reasoning-a-hamiltonian","slug":"optimizing-ai-reasoning-a-hamiltonian","title":"Optimizing AI Reasoning: A Hamiltonian Dynamics Approach to Multi-Hop Question Answering","date":"2024-10-06","arxiv_id":"2410.04415","repositories_listed":1,"syntology":null},{"url":"/paper/tubench-benchmarking-large-vision-language","slug":"tubench-benchmarking-large-vision-language","title":"TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions","date":"2024-10-05","arxiv_id":"2410.04107","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-framework-for-producing","slug":"a-general-framework-for-producing","title":"A General Framework for Producing Interpretable Semantic Text Embeddings","date":"2024-10-04","arxiv_id":"2410.03435","repositories_listed":1,"syntology":null},{"url":"/paper/exaq-exponent-aware-quantization-for-llms","slug":"exaq-exponent-aware-quantization-for-llms","title":"EXAQ: Exponent Aware Quantization For LLMs Acceleration","date":"2024-10-04","arxiv_id":"2410.03185","repositories_listed":1,"syntology":null},{"url":"/paper/table-question-answering-for-low-resourced","slug":"table-question-answering-for-low-resourced","title":"Table Question Answering for Low-resourced Indic Languages","date":"2024-10-04","arxiv_id":"2410.03576","repositories_listed":1,"syntology":null},{"url":"/paper/fastadasp-multitask-adapted-efficient","slug":"fastadasp-multitask-adapted-efficient","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","date":"2024-10-03","arxiv_id":"2410.03007","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fastadasp-multitask-adapted-efficient#ran","syntology_url":"https://syntology.ai/paper/2410.03007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03007"}},"official":{"repos":["yichen14/fastadasp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llama-slayer-8b-shallow-layers-hold-the-key","slug":"llama-slayer-8b-shallow-layers-hold-the-key","title":"Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection","date":"2024-10-03","arxiv_id":"2410.02330","repositories_listed":1,"syntology":null},{"url":"/paper/ma-rlhf-reinforcement-learning-from-human","slug":"ma-rlhf-reinforcement-learning-from-human","title":"MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions","date":"2024-10-03","arxiv_id":"2410.02743","repositories_listed":1,"syntology":null},{"url":"/paper/dlp-lora-efficient-task-specific-lora-fusion","slug":"dlp-lora-efficient-task-specific-lora-fusion","title":"DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01497","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-retrieval-in-qa-systems-with","slug":"enhancing-retrieval-in-qa-systems-with","title":"Enhancing Retrieval in QA Systems with Derived Feature Association","date":"2024-10-02","arxiv_id":"2410.03754","repositories_listed":1,"syntology":null},{"url":"/paper/question-guided-knowledge-graph-re-scoring","slug":"question-guided-knowledge-graph-re-scoring","title":"Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering","date":"2024-10-02","arxiv_id":"2410.01401","repositories_listed":1,"syntology":null},{"url":"/paper/a-hitchhikers-guide-to-fine-grained-face","slug":"a-hitchhikers-guide-to-fine-grained-face","title":"A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning","date":"2024-10-01","arxiv_id":"2410.00485","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-hitchhikers-guide-to-fine-grained-face#ran","syntology_url":"https://syntology.ai/paper/2410.00485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00485"}},"official":{"repos":["NickyFot/HitchhikersGuide"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/babelbench-an-omni-benchmark-for-code-driven","slug":"babelbench-an-omni-benchmark-for-code-driven","title":"BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data","date":"2024-10-01","arxiv_id":"2410.00773","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-large-language-model-for-continual","slug":"empowering-large-language-model-for-continual","title":"Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting","date":"2024-10-01","arxiv_id":"2410.00771","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-and-evaluating-enterprise","slug":"optimizing-and-evaluating-enterprise","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","date":"2024-10-01","arxiv_id":"2410.12812","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-parsing-with-candidate-expressions","slug":"semantic-parsing-with-candidate-expressions","title":"Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering","date":"2024-10-01","arxiv_id":"2410.00414","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-potentials-of-likelihood","slug":"unleashing-the-potentials-of-likelihood","title":"Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models","date":"2024-10-01","arxiv_id":"2410.00363","repositories_listed":1,"syntology":null},{"url":"/paper/qaencoder-towards-aligned-representation","slug":"qaencoder-towards-aligned-representation","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering System","date":"2024-09-30","arxiv_id":"2409.20434","repositories_listed":1,"syntology":null},{"url":"/paper/reference-trustable-decoding-a-training-free","slug":"reference-trustable-decoding-a-training-free","title":"Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models","date":"2024-09-30","arxiv_id":"2409.20181","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/reference-trustable-decoding-a-training-free#ran","syntology_url":"https://syntology.ai/paper/2409.20181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.20181"}},"official":{"repos":["shiluohe/referencetrustabledecoding"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/videoinsta-zero-shot-long-video-understanding","slug":"videoinsta-zero-shot-long-video-understanding","title":"VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs","date":"2024-09-30","arxiv_id":"2409.20365","repositories_listed":1,"syntology":null},{"url":"/paper/world-to-code-multi-modal-data-generation-via","slug":"world-to-code-multi-modal-data-generation-via","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","date":"2024-09-30","arxiv_id":"2409.20424","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/world-to-code-multi-modal-data-generation-via#ran","syntology_url":"https://syntology.ai/paper/2409.20424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.20424"}},"official":{"repos":["foundation-multimodal-models/world2code"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cotkr-chain-of-thought-enhanced-knowledge","slug":"cotkr-chain-of-thought-enhanced-knowledge","title":"CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering","date":"2024-09-29","arxiv_id":"2409.19753","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cotkr-chain-of-thought-enhanced-knowledge#ran","syntology_url":"https://syntology.ai/paper/2409.19753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19753"}},"official":{"repos":["wuyike2000/CoTKR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/does-rag-introduce-unfairness-in-llms#ran","syntology_url":"https://syntology.ai/paper/2409.19804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19804"}},"official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/medvilam-a-multimodal-large-language-model","slug":"medvilam-a-multimodal-large-language-model","title":"MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation","date":"2024-09-29","arxiv_id":"2409.19684","repositories_listed":1,"syntology":null},{"url":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset","slug":"t2vs-meet-vlms-a-scalable-multimodal-dataset","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","date":"2024-09-29","arxiv_id":"2409.19734","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset#ran","syntology_url":"https://syntology.ai/paper/2409.19734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19734"}},"official":{"repos":["nctu-eva-lab/vhd11k"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-extractive-question-answering","slug":"towards-robust-extractive-question-answering","title":"Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology","date":"2024-09-29","arxiv_id":"2409.19766","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-language-model-generalization-in","slug":"exploring-language-model-generalization-in","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","date":"2024-09-27","arxiv_id":"2409.18446","repositories_listed":1,"syntology":null},{"url":"/paper/disgem-distractor-generation-for-multiple","slug":"disgem-distractor-generation-for-multiple","title":"DisGeM: Distractor Generation for Multiple Choice Questions with Span Masking","date":"2024-09-26","arxiv_id":"2409.18263","repositories_listed":1,"syntology":null},{"url":"/paper/e-t-bench-towards-open-ended-event-level","slug":"e-t-bench-towards-open-ended-event-level","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","date":"2024-09-26","arxiv_id":"2409.18111","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/e-t-bench-towards-open-ended-event-level#ran","syntology_url":"https://syntology.ai/paper/2409.18111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18111"}},"official":{"repos":["PolyU-ChenLab/ETBench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/uni-med-a-unified-medical-generalist","slug":"uni-med-a-unified-medical-generalist","title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","date":"2024-09-26","arxiv_id":"2409.17508","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-temporal-ambiguity-in-questions","slug":"detecting-temporal-ambiguity-in-questions","title":"Detecting Temporal Ambiguity in Questions","date":"2024-09-25","arxiv_id":"2409.17046","repositories_listed":1,"syntology":null},{"url":"/paper/syntqa-synergistic-table-based-question","slug":"syntqa-synergistic-table-based-question","title":"SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA","date":"2024-09-25","arxiv_id":"2409.16682","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-hallucination-mitigation-framework","slug":"a-unified-hallucination-mitigation-framework","title":"A Unified Hallucination Mitigation Framework for Large Vision-Language Models","date":"2024-09-24","arxiv_id":"2409.16494","repositories_listed":1,"syntology":null},{"url":"/paper/a-zero-shot-open-vocabulary-pipeline-for","slug":"a-zero-shot-open-vocabulary-pipeline-for","title":"A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding","date":"2024-09-24","arxiv_id":"2409.15861","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-hint-generation-approaches-in-open","slug":"exploring-hint-generation-approaches-in-open","title":"Exploring Hint Generation Approaches in Open-Domain Question Answering","date":"2024-09-24","arxiv_id":"2409.16096","repositories_listed":1,"syntology":null},{"url":"/paper/konstruktor-a-strong-baseline-for-simple","slug":"konstruktor-a-strong-baseline-for-simple","title":"Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering","date":"2024-09-24","arxiv_id":"2409.15902","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-markets-a-multilingual-benchmark-to","slug":"unlocking-markets-a-multilingual-benchmark-to","title":"Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering","date":"2024-09-24","arxiv_id":"2409.16025","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-healthcare-llms-through-retrieved","slug":"boosting-healthcare-llms-through-retrieved","title":"Boosting Healthcare LLMs Through Retrieved Context","date":"2024-09-23","arxiv_id":"2409.15127","repositories_listed":1,"syntology":null},{"url":"/paper/towards-efficient-and-robust-vqa-nle-data","slug":"towards-efficient-and-robust-vqa-nle-data","title":"Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models","date":"2024-09-23","arxiv_id":"2409.14785","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-grounding-for-text-based-video","slug":"scene-text-grounding-for-text-based-video","title":"Scene-Text Grounding for Text-Based Video Question Answering","date":"2024-09-22","arxiv_id":"2409.14319","repositories_listed":1,"syntology":null},{"url":"/paper/2409-14057","slug":"2409-14057","title":"Co-occurrence is not Factual Association in Language Models","date":"2024-09-21","arxiv_id":"2409.14057","repositories_listed":1,"syntology":null},{"url":"/paper/2409-14175","slug":"2409-14175","title":"QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling","date":"2024-09-21","arxiv_id":"2409.14175","repositories_listed":1,"syntology":null},{"url":"/paper/aqa-adaptive-question-answering-in-a-society","slug":"aqa-adaptive-question-answering-in-a-society","title":"AQA: Adaptive Question Answering in a Society of LLMs via Contextual Multi-Armed Bandit","date":"2024-09-20","arxiv_id":"2409.13447","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-accuracy-optimization-computer-vision","slug":"beyond-accuracy-optimization-computer-vision","title":"Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning","date":"2024-09-20","arxiv_id":"2409.13641","repositories_listed":1,"syntology":null},{"url":"/paper/remembr-building-and-reasoning-over-long","slug":"remembr-building-and-reasoning-over-long","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","date":"2024-09-20","arxiv_id":"2409.13682","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/remembr-building-and-reasoning-over-long#ran","syntology_url":"https://syntology.ai/paper/2409.13682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13682"}},"official":{"repos":["NVIDIA-AI-IOT/remembr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/shizishangpt-an-agricultural-large-language","slug":"shizishangpt-an-agricultural-large-language","title":"ShizishanGPT: An Agricultural Large Language Model Integrating Tools and Resources","date":"2024-09-20","arxiv_id":"2409.13537","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-image-hallucination-in-text-to","slug":"evaluating-image-hallucination-in-text-to","title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","date":"2024-09-19","arxiv_id":"2409.12784","repositories_listed":1,"syntology":null},{"url":"/paper/iteration-of-thought-leveraging-inner","slug":"iteration-of-thought-leveraging-inner","title":"Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning","date":"2024-09-19","arxiv_id":"2409.12618","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-learn-to-mislead-humans-via","slug":"language-models-learn-to-mislead-humans-via","title":"Language Models Learn to Mislead Humans via RLHF","date":"2024-09-19","arxiv_id":"2409.12822","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-models-learn-to-mislead-humans-via#ran","syntology_url":"https://syntology.ai/paper/2409.12822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12822"}},"official":{"repos":["jiaxin-wen/misleadlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/development-and-bilingual-evaluation-of","slug":"development-and-bilingual-evaluation-of","title":"Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources","date":"2024-09-18","arxiv_id":"2409.11783","repositories_listed":1,"syntology":null},{"url":"/paper/tart-an-open-source-tool-augmented-framework","slug":"tart-an-open-source-tool-augmented-framework","title":"TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning","date":"2024-09-18","arxiv_id":"2409.11724","repositories_listed":1,"syntology":null},{"url":"/paper/cast-cross-modal-alignment-similarity-test","slug":"cast-cross-modal-alignment-similarity-test","title":"CAST: Cross-modal Alignment Similarity Test for Vision Language Models","date":"2024-09-17","arxiv_id":"2409.11007","repositories_listed":1,"syntology":null},{"url":"/paper/improving-llm-reasoning-with-multi-agent-tree","slug":"improving-llm-reasoning-with-multi-agent-tree","title":"Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent","date":"2024-09-17","arxiv_id":"2409.11527","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-llm-reasoning-with-multi-agent-tree#ran","syntology_url":"https://syntology.ai/paper/2409.11527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11527"}},"official":{"repos":["secureaiautonomylab/ma-tot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/less-is-more-a-simple-yet-effective-token","slug":"less-is-more-a-simple-yet-effective-token","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs","date":"2024-09-17","arxiv_id":"2409.10994","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/less-is-more-a-simple-yet-effective-token#ran","syntology_url":"https://syntology.ai/paper/2409.10994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10994"}},"official":{"repos":["freedomintelligence/trim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mamba-fusion-learning-actions-through","slug":"mamba-fusion-learning-actions-through","title":"Mamba Fusion: Learning Actions Through Questioning","date":"2024-09-17","arxiv_id":"2409.11513","repositories_listed":1,"syntology":null},{"url":"/paper/halo-hallucination-analysis-and-learning","slug":"halo-hallucination-analysis-and-learning","title":"HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making","date":"2024-09-16","arxiv_id":"2409.10011","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-to-guide-labeling-efforts-for","slug":"active-learning-to-guide-labeling-efforts-for","title":"Active Learning to Guide Labeling Efforts for Question Difficulty Estimation","date":"2024-09-14","arxiv_id":"2409.09258","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-vision-language-model-selection-for","slug":"guiding-vision-language-model-selection-for","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","date":"2024-09-14","arxiv_id":"2409.09269","repositories_listed":1,"syntology":null},{"url":"/paper/one-missing-piece-in-vision-and-language-a","slug":"one-missing-piece-in-vision-and-language-a","title":"One missing piece in Vision and Language: A Survey on Comics Understanding","date":"2024-09-14","arxiv_id":"2409.09502","repositories_listed":1,"syntology":null},{"url":"/paper/l3cube-indicquest-a-benchmark-questing","slug":"l3cube-indicquest-a-benchmark-questing","title":"L3Cube-IndicQuest: A Benchmark Question Answering Dataset for Evaluating Knowledge of LLMs in Indic Context","date":"2024-09-13","arxiv_id":"2409.08706","repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-framework-for-attributed","slug":"an-evaluation-framework-for-attributed","title":"An Evaluation Framework for Attributed Information Retrieval using Large Language Models","date":"2024-09-12","arxiv_id":"2409.08014","repositories_listed":1,"syntology":null},{"url":"/paper/adacad-adaptively-decoding-to-balance","slug":"adacad-adaptively-decoding-to-balance","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","date":"2024-09-11","arxiv_id":"2409.07394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adacad-adaptively-decoding-to-balance#ran","syntology_url":"https://syntology.ai/paper/2409.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07394"}},"official":{"repos":["hannight/adacad"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/2409-13731","slug":"2409-13731","title":"KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation","date":"2024-09-10","arxiv_id":"2409.13731","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2409-13731#ran","syntology_url":"https://syntology.ai/paper/2409.13731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13731"}},"official":{"repos":["openspg/kag"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/eyeclip-a-visual-language-foundation-model","slug":"eyeclip-a-visual-language-foundation-model","title":"EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis","date":"2024-09-10","arxiv_id":"2409.06644","repositories_listed":1,"syntology":null},{"url":"/paper/grouse-a-benchmark-to-evaluate-evaluators-in","slug":"grouse-a-benchmark-to-evaluate-evaluators-in","title":"GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering","date":"2024-09-10","arxiv_id":"2409.06595","repositories_listed":1,"syntology":null},{"url":"/paper/alt-moe-multimodal-alignment-via-alternating","slug":"alt-moe-multimodal-alignment-via-alternating","title":"M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework","date":"2024-09-09","arxiv_id":"2409.05929","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alt-moe-multimodal-alignment-via-alternating#ran","syntology_url":"https://syntology.ai/paper/2409.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05929"}},"official":{"repos":["HongyangLL/M3-JEPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memorag-moving-towards-next-gen-rag-via","slug":"memorag-moving-towards-next-gen-rag-via","title":"MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery","date":"2024-09-09","arxiv_id":"2409.05591","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/memorag-moving-towards-next-gen-rag-via#ran","syntology_url":"https://syntology.ai/paper/2409.05591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05591"}},"official":{"repos":["qhjqhj00/memorag"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/shaking-up-vlms-comparing-transformers-and","slug":"shaking-up-vlms-comparing-transformers-and","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","date":"2024-09-09","arxiv_id":"2409.05395","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shaking-up-vlms-comparing-transformers-and#ran","syntology_url":"https://syntology.ai/paper/2409.05395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05395"}},"official":{"repos":["gpantaz/vl_mamba"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/just-asr-llm-a-study-on-speech-large-language","slug":"just-asr-llm-a-study-on-speech-large-language","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","date":"2024-09-07","arxiv_id":"2409.04927","repositories_listed":1,"syntology":null},{"url":"/paper/columbus-evaluating-cognitive-lateral","slug":"columbus-evaluating-cognitive-lateral","title":"COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes","date":"2024-09-06","arxiv_id":"2409.04053","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/columbus-evaluating-cognitive-lateral#ran","syntology_url":"https://syntology.ai/paper/2409.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04053"}},"official":{"repos":["koen-47/columbus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/question-answering-dense-video-events","slug":"question-answering-dense-video-events","title":"Question-Answering Dense Video Events","date":"2024-09-06","arxiv_id":"2409.04388","repositories_listed":1,"syntology":null},{"url":"/paper/debate-on-graph-a-flexible-and-reliable","slug":"debate-on-graph-a-flexible-and-reliable","title":"Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models","date":"2024-09-05","arxiv_id":"2409.03155","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debate-on-graph-a-flexible-and-reliable#ran","syntology_url":"https://syntology.ai/paper/2409.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03155"}},"official":{"repos":["reml-group/dog"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-healthcare-llm-trust-with-atypical","slug":"enhancing-healthcare-llm-trust-with-atypical","title":"Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration","date":"2024-09-05","arxiv_id":"2409.03225","repositories_listed":1,"syntology":null},{"url":"/paper/lexicon3d-probing-visual-foundation-models","slug":"lexicon3d-probing-visual-foundation-models","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","date":"2024-09-05","arxiv_id":"2409.03757","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lexicon3d-probing-visual-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2409.03757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03757"}},"official":null}},{"url":"/paper/mplug-docowl2-high-resolution-compressing-for","slug":"mplug-docowl2-high-resolution-compressing-for","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","date":"2024-09-05","arxiv_id":"2409.03420","repositories_listed":1,"syntology":null},{"url":"/paper/the-representation-landscape-of-few-shot","slug":"the-representation-landscape-of-few-shot","title":"The representation landscape of few-shot learning and fine-tuning in large language models","date":"2024-09-05","arxiv_id":"2409.03662","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-representation-landscape-of-few-shot#ran","syntology_url":"https://syntology.ai/paper/2409.03662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03662"}},"official":{"repos":["diegodoimo/geometry_icl_finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/longcite-enabling-llms-to-generate-fine","slug":"longcite-enabling-llms-to-generate-fine","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","date":"2024-09-04","arxiv_id":"2409.02897","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longcite-enabling-llms-to-generate-fine#ran","syntology_url":"https://syntology.ai/paper/2409.02897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02897"}},"official":{"repos":["THUDM/LongCite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/craft-your-dataset-task-specific-synthetic","slug":"craft-your-dataset-task-specific-synthetic","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","date":"2024-09-03","arxiv_id":"2409.02098","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-determine-the-preferred-image","slug":"how-to-determine-the-preferred-image","title":"How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?","date":"2024-09-03","arxiv_id":"2409.02253","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-to-determine-the-preferred-image#ran","syntology_url":"https://syntology.ai/paper/2409.02253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02253"}},"official":{"repos":["asgsaeid/cad_vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vprochart-answering-chart-question-through","slug":"vprochart-answering-chart-question-through","title":"VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning","date":"2024-09-03","arxiv_id":"2409.01667","repositories_listed":1,"syntology":null},{"url":"/paper/what-are-the-essential-factors-in-crafting","slug":"what-are-the-essential-factors-in-crafting","title":"What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices","date":"2024-09-03","arxiv_id":"2409.01893","repositories_listed":1,"syntology":null}],"record_sha256":"fff94a2a9f16aa40aaeadc9a29377e9491a307f65704e604e8a5f61f6689d605","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}