{"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/54","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":54,"pages_in_order":109,"rows_per_page":100,"rows":[5301,5400],"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/53","next":"/task/question-answering/papers/55","papers":[{"url":null,"slug":"ahp-powered-llm-reasoning-for-multi-criteria","title":"AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses","date":"2024-10-02","arxiv_id":"2410.01246","repositories_listed":0,"syntology":null},{"url":null,"slug":"backdooring-vision-language-models-with-out","title":"Backdooring Vision-Language Models with Out-Of-Distribution Data","date":"2024-10-02","arxiv_id":"2410.01264","repositories_listed":0,"syntology":null},{"url":"/paper/bridging-context-gaps-leveraging-coreference","slug":"bridging-context-gaps-leveraging-coreference","title":"Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding","date":"2024-10-02","arxiv_id":"2410.01671","repositories_listed":0,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/bridging-context-gaps-leveraging-coreference#ran","syntology_url":"https://syntology.ai/paper/2410.01671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01671"}},"official":null}},{"url":null,"slug":"calf-benchmarking-evaluation-of-lfqa-using","title":"CALF: Benchmarking Evaluation of LFQA Using Chinese Examinations","date":"2024-10-02","arxiv_id":"2410.01945","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcqpr-proactive-conversational-question","title":"PCQPR: Proactive Conversational Question Planning with Reflection","date":"2024-10-02","arxiv_id":"2410.01363","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-elicitation-in-language-models-via","title":"Reasoning Elicitation in Language Models via Counterfactual Feedback","date":"2024-10-02","arxiv_id":"2410.03767","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-context-matters-in-vqa-and-reasoning","title":"Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities","date":"2024-10-02","arxiv_id":"2410.01690","repositories_listed":0,"syntology":null},{"url":null,"slug":"addition-is-all-you-need-for-energy-efficient","title":"Addition is All You Need for Energy-efficient Language Models","date":"2024-10-01","arxiv_id":"2410.00907","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-large-language-models-for-3","title":"Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents","date":"2024-10-01","arxiv_id":"2410.00526","repositories_listed":0,"syntology":null},{"url":null,"slug":"fmbench-benchmarking-fairness-in-multimodal","title":"FMBench: Benchmarking Fairness in Multimodal Large Language Models on Medical Tasks","date":"2024-10-01","arxiv_id":"2410.01089","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-reliance-on-external-information","title":"Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis","date":"2024-10-01","arxiv_id":"2410.00857","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-updatable-large-language-models-with","title":"Self-Updatable Large Language Models with Parameter Integration","date":"2024-10-01","arxiv_id":"2410.00487","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-then-tell-enhancing-key-information","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","date":"2024-09-29","arxiv_id":"2409.19573","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-dataflywheel-resolving-the-impossible","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","date":"2024-09-29","arxiv_id":"2409.19532","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-ct-gpt-generating-3d-radiology-reports","title":"3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models","date":"2024-09-28","arxiv_id":"2409.19330","repositories_listed":0,"syntology":null},{"url":null,"slug":"healthq-unveiling-questioning-capabilities-of","title":"HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations","date":"2024-09-28","arxiv_id":"2409.19487","repositories_listed":0,"syntology":null},{"url":null,"slug":"trojvlm-backdoor-attack-against-vision","title":"TrojVLM: Backdoor Attack Against Vision Language Models","date":"2024-09-28","arxiv_id":"2409.19232","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-multi-hop-question-answering-via","title":"Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models","date":"2024-09-28","arxiv_id":"2409.19382","repositories_listed":0,"syntology":null},{"url":null,"slug":"aipatient-simulating-patients-with-ehrs-and","title":"AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow","date":"2024-09-27","arxiv_id":"2409.18924","repositories_listed":0,"syntology":null},{"url":null,"slug":"charting-the-future-using-chart-question","title":"Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations","date":"2024-09-27","arxiv_id":"2409.18764","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-explainability-in-multimodal-large","title":"Enhancing Explainability in Multimodal Large Language Models Using Ontological Context","date":"2024-09-27","arxiv_id":"2409.18753","repositories_listed":0,"syntology":null},{"url":null,"slug":"rehearsing-answers-to-probable-questions-with","title":"Rehearsing Answers to Probable Questions with Perspective-Taking","date":"2024-09-27","arxiv_id":"2409.18678","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-superficial-alignment","title":"Revisiting the Superficial Alignment Hypothesis","date":"2024-09-27","arxiv_id":"2410.03717","repositories_listed":0,"syntology":null},{"url":null,"slug":"dare-diverse-visual-question-answering-with","title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","date":"2024-09-26","arxiv_id":"2409.18023","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-in-domain-question-answering-for","title":"Efficient In-Domain Question Answering for Resource-Constrained Environments","date":"2024-09-26","arxiv_id":"2409.17648","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-memory-verbalization-using","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","date":"2024-09-26","arxiv_id":"2409.17702","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-hierarchical-semantic-into","title":"Integrating Hierarchical Semantic into Iterative Generation Model for Entailment Tree Explanation","date":"2024-09-26","arxiv_id":"2409.17757","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-environmental-state-recognition-with","title":"Robotic Environmental State Recognition with Pre-Trained Vision-Language Models and Black-Box Optimization","date":"2024-09-26","arxiv_id":"2409.17519","repositories_listed":0,"syntology":null},{"url":null,"slug":"t3-a-novel-zero-shot-transfer-learning","title":"T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task","date":"2024-09-26","arxiv_id":"2409.17640","repositories_listed":0,"syntology":null},{"url":null,"slug":"zalm3-zero-shot-enhancement-of-vision","title":"ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue","date":"2024-09-26","arxiv_id":"2409.17610","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-post-hoc-attributions-in-long","title":"Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition","date":"2024-09-25","arxiv_id":"2409.17073","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-temporal-sensitivity-and-reasoning","title":"Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering","date":"2024-09-25","arxiv_id":"2409.16909","repositories_listed":0,"syntology":null},{"url":null,"slug":"asthmabot-multi-modal-multi-lingual-retrieval","title":"AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support","date":"2024-09-24","arxiv_id":"2409.15815","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-insights-on-fine-tuning-large","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","date":"2024-09-24","arxiv_id":"2409.15825","repositories_listed":0,"syntology":null},{"url":null,"slug":"expert-level-vision-language-foundation-model","title":"Expert-level vision-language foundation model for real-world radiology and comprehensive evaluation","date":"2024-09-24","arxiv_id":"2409.16183","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-pixels-to-words-leveraging","title":"From Pixels to Words: Leveraging Explainability in Face Recognition through Interactive Natural Language Processing","date":"2024-09-24","arxiv_id":"2409.16089","repositories_listed":0,"syntology":null},{"url":null,"slug":"lighter-and-better-towards-flexible-context","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","date":"2024-09-24","arxiv_id":"2409.15699","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-preliminary-study-of-o1-in-medicine-are-we","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","date":"2024-09-23","arxiv_id":"2409.15277","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-clip-count-stars-an-empirical-study-on","title":"Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP","date":"2024-09-23","arxiv_id":"2409.15035","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect-describe-discriminate-moving-beyond","title":"Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation","date":"2024-09-23","arxiv_id":"2409.15125","repositories_listed":0,"syntology":null},{"url":null,"slug":"gem-rag-graphical-eigen-memories-for","title":"GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation","date":"2024-09-23","arxiv_id":"2409.15566","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-when-to-retrieve-what-to-rewrite-and","title":"Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA","date":"2024-09-23","arxiv_id":"2409.15515","repositories_listed":0,"syntology":null},{"url":null,"slug":"linkage-listwise-ranking-among-varied-quality","title":"LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs","date":"2024-09-23","arxiv_id":"2409.14744","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-similarity-to-evaluate-factual","title":"Using Similarity to Evaluate Factual Consistency in Summaries","date":"2024-09-23","arxiv_id":"2409.15090","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-performance-and-robustness-of","title":"Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions","date":"2024-09-22","arxiv_id":"2409.14572","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13992","title":"SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval","date":"2024-09-21","arxiv_id":"2409.13992","repositories_listed":0,"syntology":null},{"url":null,"slug":"bench-benchmarking-vision-language-models-for","title":"@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology","date":"2024-09-21","arxiv_id":"2409.14215","repositories_listed":0,"syntology":null},{"url":null,"slug":"drift-to-remember","title":"Drift to Remember","date":"2024-09-21","arxiv_id":"2409.13997","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-dense-retrieval-approach-for","title":"A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering","date":"2024-09-20","arxiv_id":"2409.13483","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-models-with-domain","title":"Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology","date":"2024-09-20","arxiv_id":"2409.13902","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-place-solution-to-the-multiple-choice","title":"First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge","date":"2024-09-20","arxiv_id":"2409.13538","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-memorization-in-large-language","title":"Unlocking Memorization in Large Language Models with Dynamic Soft Prompting","date":"2024-09-20","arxiv_id":"2409.13853","repositories_listed":0,"syntology":null},{"url":null,"slug":"cameleval-advancing-culturally-aligned-arabic","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","date":"2024-09-19","arxiv_id":"2409.12623","repositories_listed":0,"syntology":null},{"url":null,"slug":"edu-values-towards-evaluating-the-chinese","title":"Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models","date":"2024-09-19","arxiv_id":"2409.12739","repositories_listed":0,"syntology":null},{"url":null,"slug":"taco-rl-task-aware-prompt-compression","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","date":"2024-09-19","arxiv_id":"2409.13035","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-can-parse-floor-plan","title":"Vision Language Models Can Parse Floor Plan Maps","date":"2024-09-19","arxiv_id":"2409.12842","repositories_listed":0,"syntology":null},{"url":null,"slug":"finetuning-language-models-to-emit-linguistic","title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","date":"2024-09-18","arxiv_id":"2409.12180","repositories_listed":0,"syntology":null},{"url":null,"slug":"mqa-keal-multi-hop-question-answering-under","title":"MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language","date":"2024-09-18","arxiv_id":"2409.12257","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-breach-assessing-the-robustness-of","title":"Contextual Breach: Assessing the Robustness of Transformer-based QA Models","date":"2024-09-17","arxiv_id":"2409.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"oneencoder-a-lightweight-framework-for","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","date":"2024-09-17","arxiv_id":"2409.11059","repositories_listed":0,"syntology":null},{"url":null,"slug":"proslm-a-prolog-synergized-language-model-for","title":"ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering","date":"2024-09-17","arxiv_id":"2409.11589","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparks-of-artificial-general-intelligence-agi","title":"Sparks of Artificial General Intelligence(AGI) in Semiconductor Material Science: Early Explorations into the Next Frontier of Generative AI-Assisted Electron Micrograph Analysis","date":"2024-09-17","arxiv_id":"2409.12244","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-guided-self-questioning-and","title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment","date":"2024-09-17","arxiv_id":"2410.02768","repositories_listed":0,"syntology":null},{"url":null,"slug":"struedit-structured-outputs-enable-the-fast","title":"StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models","date":"2024-09-16","arxiv_id":"2409.10132","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-benchmark-dataset-with-larger-context-for","title":"A Benchmark Dataset with Larger Context for Non-Factoid Question Answering over Islamic Text","date":"2024-09-15","arxiv_id":"2409.09844","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-the-hallucination-on-low-level","title":"Explore the Hallucination on Low-level Perception for MLLMs","date":"2024-09-15","arxiv_id":"2409.09748","repositories_listed":0,"syntology":null},{"url":null,"slug":"nevlp-noise-robust-framework-for-efficient","title":"NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training","date":"2024-09-15","arxiv_id":"2409.09582","repositories_listed":0,"syntology":null},{"url":null,"slug":"qtg-vqa-question-type-guided-architectural","title":"QTG-VQA: Question-Type-Guided Architectural for VideoQA Systems","date":"2024-09-14","arxiv_id":"2409.09348","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-evaluation-of-large-language","title":"Contextual Evaluation of Large Language Models for Classifying Tropical and Infectious Diseases","date":"2024-09-13","arxiv_id":"2409.09201","repositories_listed":0,"syntology":null},{"url":null,"slug":"contri-e-ve-context-retrieve-for-scholarly","title":"Contri(e)ve: Context + Retrieve for Scholarly Question Answering","date":"2024-09-13","arxiv_id":"2409.09010","repositories_listed":0,"syntology":null},{"url":null,"slug":"electrocardiogram-report-generation-and","title":"Electrocardiogram Report Generation and Question Answering via Retrieval-Augmented Self-Supervised Modeling","date":"2024-09-13","arxiv_id":"2409.08788","repositories_listed":0,"syntology":null},{"url":null,"slug":"expediting-and-elevating-large-language-model","title":"Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding","date":"2024-09-13","arxiv_id":"2409.08561","repositories_listed":0,"syntology":null},{"url":null,"slug":"kodexv0-1-a-family-of-state-of-the-art","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","date":"2024-09-13","arxiv_id":"2409.13749","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-q-a-text-retrieval-with-ranking","title":"Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG","date":"2024-09-12","arxiv_id":"2409.07691","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimenting-with-legal-ai-solutions-the","title":"Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice","date":"2024-09-12","arxiv_id":"2409.07713","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-object-event-graph-representation","title":"Multi-object event graph representation learning for Video Question Answering","date":"2024-09-12","arxiv_id":"2409.07747","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniquery-contextually-augmenting-captured","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","date":"2024-09-12","arxiv_id":"2409.08250","repositories_listed":0,"syntology":null},{"url":null,"slug":"source2synth-synthetic-data-generation-and","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","date":"2024-09-12","arxiv_id":"2409.08239","repositories_listed":0,"syntology":null},{"url":null,"slug":"top-down-activity-representation-learning-for","title":"Top-down Activity Representation Learning for Video Question Answering","date":"2024-09-12","arxiv_id":"2409.07748","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-sparql-and-llms-for-question","title":"Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources","date":"2024-09-11","arxiv_id":"2409.18969","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-compress-contexts-for-efficient","title":"Learning to Compress Contexts for Efficient Knowledge-based Visual Question Answering","date":"2024-09-11","arxiv_id":"2409.07331","repositories_listed":0,"syntology":null},{"url":null,"slug":"medic-towards-a-comprehensive-framework-for","title":"MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications","date":"2024-09-11","arxiv_id":"2409.07314","repositories_listed":0,"syntology":null},{"url":null,"slug":"securing-vision-language-models-with-a-robust","title":"Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks","date":"2024-09-11","arxiv_id":"2409.07353","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-large-language-model-pretraining","title":"Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review","date":"2024-09-10","arxiv_id":"2409.06131","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-temporal-understanding-in-audio","title":"Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models","date":"2024-09-10","arxiv_id":"2409.06223","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-in-visual-language-1","title":"Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding","date":"2024-09-10","arxiv_id":"2409.06485","repositories_listed":0,"syntology":null},{"url":null,"slug":"visscience-an-extensive-benchmark-for","title":"VisScience: An Extensive Benchmark for Evaluating K12 Educational Multi-modal Scientific Reasoning","date":"2024-09-10","arxiv_id":"2409.13730","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-neural-network-scaling-laws-with","title":"Breaking Neural Network Scaling Laws with Modularity","date":"2024-09-09","arxiv_id":"2409.05780","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-fl-multimodal-large-language-model","title":"MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning","date":"2024-09-09","arxiv_id":"2409.06067","repositories_listed":0,"syntology":null},{"url":null,"slug":"seek-and-solve-reasoning-for-table-question","title":"Seek and Solve Reasoning for Table Question Answering","date":"2024-09-09","arxiv_id":"2409.05286","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-a-robust-knowledge-intensive","title":"Towards Building a Robust Knowledge Intensive Question Answering Model with Large Language Models","date":"2024-09-09","arxiv_id":"2409.05385","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-llms-and-knowledge-graphs-to-reduce","title":"Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Question Answering","date":"2024-09-06","arxiv_id":"2409.04181","repositories_listed":0,"syntology":null},{"url":null,"slug":"webquest-a-benchmark-for-multimodal-qa-on-web","title":"WebQuest: A Benchmark for Multimodal QA on Web Page Sequences","date":"2024-09-06","arxiv_id":"2409.13711","repositories_listed":0,"syntology":null},{"url":null,"slug":"marags-a-multi-adapter-system-for-multi-task","title":"MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question Answering","date":"2024-09-05","arxiv_id":"2409.03171","repositories_listed":0,"syntology":null},{"url":null,"slug":"occllama-an-occupancy-language-action","title":"OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving","date":"2024-09-05","arxiv_id":"2409.03272","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-based-question-answering-for-contextual","title":"RAG based Question-Answering for Contextual Response Prediction System","date":"2024-09-05","arxiv_id":"2409.03708","repositories_listed":0,"syntology":null},{"url":null,"slug":"vietnamese-legal-information-retrieval-in","title":"Vietnamese Legal Information Retrieval in Question-Answering System","date":"2024-09-05","arxiv_id":"2409.13699","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversify-verify-adapt-efficient-and-robust","title":"Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering","date":"2024-09-04","arxiv_id":"2409.02361","repositories_listed":0,"syntology":null},{"url":null,"slug":"got-cqa-graph-of-thought-guided-compositional","title":"GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering","date":"2024-09-04","arxiv_id":"2409.02611","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-privacy-savvy-are-large-language-models-a","title":"How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review","date":"2024-09-04","arxiv_id":"2409.02375","repositories_listed":0,"syntology":null}],"record_sha256":"222be2864d4a4bfdaf2e64ea41ba83e3ccbee27174b5707272df7b5b2793927a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}