{"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/61","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":61,"pages_in_order":109,"rows_per_page":100,"rows":[6001,6100],"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/60","next":"/task/question-answering/papers/62","papers":[{"url":null,"slug":"tv-trees-multimodal-entailment-trees-for","title":"TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning","date":"2024-02-29","arxiv_id":"2402.19467","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cognitive-evaluation-benchmark-of-image","title":"A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models","date":"2024-02-28","arxiv_id":"2402.18409","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-gpt-improve-the-state-of-prior","title":"Can GPT Improve the State of Prior Authorization via Guideline Based Automated Question Answering?","date":"2024-02-28","arxiv_id":"2402.18419","repositories_listed":0,"syntology":null},{"url":null,"slug":"arcsin-adaptive-ranged-cosine-similarity","title":"ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks","date":"2024-02-27","arxiv_id":"2402.17298","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-in-conversation-solving-subjective","title":"Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models","date":"2024-02-27","arxiv_id":"2402.17226","repositories_listed":0,"syntology":null},{"url":"/paper/researchy-questions-a-dataset-of-multi","slug":"researchy-questions-a-dataset-of-multi","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","date":"2024-02-27","arxiv_id":"2402.17896","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-refinement-of-language-models-from","title":"Self-Refinement of Language Models from External Proxy Metrics Feedback","date":"2024-02-27","arxiv_id":"2403.00827","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-multiple-choices-question","title":"Unsupervised multiple choices question answering via universal corpus","date":"2024-02-27","arxiv_id":"2402.17333","repositories_listed":0,"syntology":null},{"url":null,"slug":"vcd-knowledge-base-guided-visual-commonsense","title":"VCD: Knowledge Base Guided Visual Commonsense Discovery in Images","date":"2024-02-27","arxiv_id":"2402.17213","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfret-dvqa-coarse-to-fine-retrieval-and","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","date":"2024-02-26","arxiv_id":"2403.00816","repositories_listed":0,"syntology":null},{"url":null,"slug":"gigapevt-multimodal-medical-assistant","title":"GigaPevt: Multimodal Medical Assistant","date":"2024-02-26","arxiv_id":"2402.16654","repositories_listed":0,"syntology":null},{"url":null,"slug":"paqa-toward-proactive-open-retrieval-question","title":"PAQA: Toward ProActive Open-Retrieval Question Answering","date":"2024-02-26","arxiv_id":"2402.16608","repositories_listed":0,"syntology":null},{"url":null,"slug":"perltqa-a-personal-long-term-memory-dataset","title":"PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering","date":"2024-02-26","arxiv_id":"2402.16288","repositories_listed":0,"syntology":null},{"url":null,"slug":"rainbow-teaming-open-ended-generation-of","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","date":"2024-02-26","arxiv_id":"2402.16822","repositories_listed":0,"syntology":null},{"url":"/paper/two-stage-generative-question-answering-on","slug":"two-stage-generative-question-answering-on","title":"Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models","date":"2024-02-26","arxiv_id":"2402.16568","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-approaches-for-improving","title":"Deep Learning Approaches for Improving Question Answering Systems in Hepatocellular Carcinoma Research","date":"2024-02-25","arxiv_id":"2402.16038","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-perturbation-consistency-learning-for","title":"Prompt Perturbation Consistency Learning for Robust Language Models","date":"2024-02-24","arxiv_id":"2402.15833","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabiangpt-native-arabic-gpt-based-large","title":"ArabianGPT: Native Arabic GPT-based Large Language Model","date":"2024-02-23","arxiv_id":"2402.15313","repositories_listed":0,"syntology":null},{"url":null,"slug":"cost-adaptive-recourse-recommendation-by","title":"Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation","date":"2024-02-23","arxiv_id":"2402.15073","repositories_listed":0,"syntology":null},{"url":null,"slug":"dosa-a-dataset-of-social-artifacts-from","title":"DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures","date":"2024-02-23","arxiv_id":"2403.14651","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-performance-of-chatgpt-for","title":"Evaluating the Performance of ChatGPT for Spam Email Detection","date":"2024-02-23","arxiv_id":"2402.15537","repositories_listed":0,"syntology":null},{"url":"/paper/faithful-temporal-question-answering-over","slug":"faithful-temporal-question-answering-over","title":"Faithful Temporal Question Answering over Heterogeneous Sources","date":"2024-02-23","arxiv_id":"2402.15400","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-transformer-with-a-low","title":"Multimodal Transformer With a Low-Computational-Cost Guarantee","date":"2024-02-23","arxiv_id":"2402.15096","repositories_listed":0,"syntology":null},{"url":null,"slug":"visreas-complex-visual-reasoning-with","title":"VISREAS: Complex Visual Reasoning with Unanswerable Questions","date":"2024-02-23","arxiv_id":"2403.10534","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-the-generator-mind-its-contexts-an","title":"Does the Generator Mind its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer","date":"2024-02-22","arxiv_id":"2402.14488","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-sequence-entropy-towards-uncertainty","title":"Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond","date":"2024-02-22","arxiv_id":"2402.14259","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-meet-long-video-advancing-long-video","title":"LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs","date":"2024-02-21","arxiv_id":"2402.13546","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-dc-when-to-retrieve-and-when-to-generate","title":"Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions","date":"2024-02-21","arxiv_id":"2402.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-frontier-of-vision-language","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","date":"2024-02-20","arxiv_id":"2404.07214","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-impact-of-table-to-text-methods","title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","date":"2024-02-20","arxiv_id":"2402.12869","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-aware-integration-with-large","title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering","date":"2024-02-20","arxiv_id":"2402.12728","repositories_listed":0,"syntology":null},{"url":"/paper/question-calibration-and-multi-hop-modeling","slug":"question-calibration-and-multi-hop-modeling","title":"Question Calibration and Multi-Hop Modeling for Temporal Question Answering","date":"2024-02-20","arxiv_id":"2402.13188","repositories_listed":0,"syntology":null},{"url":null,"slug":"slot-vlm-slowfast-slots-for-video-language","title":"Slot-VLM: SlowFast Slots for Video-Language Modeling","date":"2024-02-20","arxiv_id":"2402.13088","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoprism-a-foundational-visual-encoder-for","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","date":"2024-02-20","arxiv_id":"2402.13217","repositories_listed":0,"syntology":null},{"url":null,"slug":"bider-bridging-knowledge-inconsistency-for","title":"BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence","date":"2024-02-19","arxiv_id":"2402.12174","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-retriever-captures-the-long-tail","title":"Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge","date":"2024-02-19","arxiv_id":"2402.12352","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-tailor-mitigating-catastrophic","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","date":"2024-02-19","arxiv_id":"2402.12048","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrke-the-multi-hop-reasoning-evaluation-of","title":"Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark","date":"2024-02-19","arxiv_id":"2402.11924","repositories_listed":0,"syntology":null},{"url":null,"slug":"rjua-meddqa-a-multimodal-benchmark-for","title":"RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning","date":"2024-02-19","arxiv_id":"2402.14840","repositories_listed":0,"syntology":null},{"url":null,"slug":"tables-as-images-exploring-the-strengths-and","title":"Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs","date":"2024-02-19","arxiv_id":"2402.12424","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-table-question-answering-via-sql","title":"Training Table Question Answering via SQL Query Decomposition","date":"2024-02-19","arxiv_id":"2402.13288","repositories_listed":0,"syntology":null},{"url":null,"slug":"counter-intuitive-large-language-models-can","title":"Large Language Models Can Better Understand Knowledge Graphs Than We Thought","date":"2024-02-18","arxiv_id":"2402.11541","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-answering-over-spatio-temporal","title":"Question Answering Over Spatio-Temporal Knowledge Graph","date":"2024-02-18","arxiv_id":"2402.11542","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-question-answering-based-pipeline-for","title":"A Question Answering Based Pipeline for Comprehensive Chinese EHR Information Extraction","date":"2024-02-17","arxiv_id":"2402.11177","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-llms-mathematical-reasoning-in","title":"Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering","date":"2024-02-17","arxiv_id":"2402.11194","repositories_listed":0,"syntology":null},{"url":null,"slug":"cliqueparcel-an-approach-for-batching-llm","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","date":"2024-02-17","arxiv_id":"2402.14833","repositories_listed":0,"syntology":null},{"url":null,"slug":"gendec-a-robust-generative-question","title":"GenDec: A robust generative Question-decomposition method for Multi-hop reasoning","date":"2024-02-17","arxiv_id":"2402.11166","repositories_listed":0,"syntology":null},{"url":null,"slug":"blendfilter-advancing-retrieval-augmented","title":"BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering","date":"2024-02-16","arxiv_id":"2402.11129","repositories_listed":0,"syntology":null},{"url":null,"slug":"construction-of-a-syntactic-analysis-map-for","title":"Construction of a Syntactic Analysis Map for Yi Shui School through Text Mining and Natural Language Processing Research","date":"2024-02-16","arxiv_id":"2402.10743","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-hybrid-question-answering-via","title":"Exploring Hybrid Question Answering via Program-based Prompting","date":"2024-02-16","arxiv_id":"2402.10812","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-to-the-best-explanation-in-large","title":"Inference to the Best Explanation in Large Language Models","date":"2024-02-16","arxiv_id":"2402.10767","repositories_listed":0,"syntology":null},{"url":null,"slug":"palm2-vadapter-progressively-aligned-language","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","date":"2024-02-16","arxiv_id":"2402.10896","repositories_listed":0,"syntology":null},{"url":null,"slug":"pat-questions-a-self-updating-benchmark-for","title":"PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering","date":"2024-02-16","arxiv_id":"2402.11034","repositories_listed":0,"syntology":null},{"url":"/paper/vqattack-transferable-adversarial-attacks-on","slug":"vqattack-transferable-adversarial-attacks-on","title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","date":"2024-02-16","arxiv_id":"2402.11083","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vqattack-transferable-adversarial-attacks-on#ran","syntology_url":"https://syntology.ai/paper/2402.11083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11083"}},"official":null}},{"url":null,"slug":"zero-shot-sampling-of-adversarial-entities-in","title":"Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks","date":"2024-02-16","arxiv_id":"2402.10527","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dataset-of-open-domain-question-answering","title":"A Dataset of Open-Domain Question Answering with Multiple-Span Answers","date":"2024-02-15","arxiv_id":"2402.09923","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-models-with-pseudo","title":"Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering","date":"2024-02-15","arxiv_id":"2402.09911","repositories_listed":0,"syntology":null},{"url":"/paper/lapdoc-layout-aware-prompting-for-documents","slug":"lapdoc-layout-aware-prompting-for-documents","title":"LAPDoc: Layout-Aware Prompting for Documents","date":"2024-02-15","arxiv_id":"2402.09841","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-personalized-federated-learning","title":"Prompt-based Personalized Federated Learning for Medical Visual Question Answering","date":"2024-02-15","arxiv_id":"2402.09677","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-query-focused-disaster-summarization","title":"Multi-Query Focused Disaster Summarization via Instruction-Based Prompting","date":"2024-02-14","arxiv_id":"2402.09008","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-how-to-ask-cycle-consistency-refines","title":"Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models","date":"2024-02-13","arxiv_id":"2402.08756","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-question-answering-instruction","title":"Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks","date":"2024-02-13","arxiv_id":"2402.08360","repositories_listed":0,"syntology":null},{"url":null,"slug":"bdiqa-a-new-dataset-for-video-question","title":"BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind","date":"2024-02-12","arxiv_id":"2402.07402","repositories_listed":0,"syntology":null},{"url":null,"slug":"lumos-empowering-multimodal-llms-with-scene","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","date":"2024-02-12","arxiv_id":"2402.08017","repositories_listed":0,"syntology":null},{"url":null,"slug":"pivot-iterative-visual-prompting-elicits","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","date":"2024-02-12","arxiv_id":"2402.07872","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-thought-process-as","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","date":"2024-02-12","arxiv_id":"2402.07812","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-rag-lessons-from-the-llm-trenches","title":"T-RAG: Lessons from the LLM Trenches","date":"2024-02-12","arxiv_id":"2402.07483","repositories_listed":0,"syntology":null},{"url":null,"slug":"cpsdbench-a-large-language-model-evaluation","title":"CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain","date":"2024-02-11","arxiv_id":"2402.07234","repositories_listed":0,"syntology":null},{"url":null,"slug":"fabert-pre-training-bert-on-persian-blogs","title":"FaBERT: Pre-training BERT on Persian Blogs","date":"2024-02-09","arxiv_id":"2402.06617","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-generative-ai-paradox-on-evaluation-what","title":"The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluate","date":"2024-02-09","arxiv_id":"2402.06204","repositories_listed":0,"syntology":null},{"url":null,"slug":"cic-a-framework-for-culturally-aware-image","title":"CIC: A Framework for Culturally-Aware Image Captioning","date":"2024-02-08","arxiv_id":"2402.05374","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-models-for-the-detection-of-hate","title":"Efficient Models for the Detection of Hate, Abuse and Profanity","date":"2024-02-08","arxiv_id":"2402.05624","repositories_listed":0,"syntology":null},{"url":null,"slug":"faq-gen-an-automated-system-to-generate","title":"FAQ-Gen: An automated system to generate domain-specific FAQs to aid content comprehension","date":"2024-02-08","arxiv_id":"2402.05812","repositories_listed":0,"syntology":null},{"url":null,"slug":"subgen-token-generation-in-sublinear-time-and","title":"SubGen: Token Generation in Sublinear Time and Memory","date":"2024-02-08","arxiv_id":"2402.06082","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-language-models-with-active","title":"Empowering Language Models with Active Inquiry for Deeper Understanding","date":"2024-02-06","arxiv_id":"2402.03719","repositories_listed":0,"syntology":null},{"url":null,"slug":"minds-versus-machines-rethinking-entailment","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","date":"2024-02-06","arxiv_id":"2402.03686","repositories_listed":0,"syntology":null},{"url":null,"slug":"scemqa-a-scientific-college-entrance-level","title":"SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark","date":"2024-02-06","arxiv_id":"2402.05138","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-survey-of-prompt-engineering-in","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","date":"2024-02-05","arxiv_id":"2402.07927","repositories_listed":0,"syntology":null},{"url":null,"slug":"lb-kbqa-large-language-model-and-bert-based","title":"LB-KBQA: Large-language-model and BERT based Knowledge-Based Question and Answering System","date":"2024-02-05","arxiv_id":"2402.05130","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-bayesian-multi-perspective","title":"eXplainable Bayesian Multi-Perspective Generative Retrieval","date":"2024-02-04","arxiv_id":"2402.02418","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-for-table-processing-a","title":"Large Language Model for Table Processing: A Survey","date":"2024-02-04","arxiv_id":"2402.05121","repositories_listed":0,"syntology":null},{"url":null,"slug":"puzzlebench-can-llms-solve-challenging-first","title":"PuzzleBench: Can LLMs Solve Challenging First-Order Combinatorial Reasoning Problems?","date":"2024-02-04","arxiv_id":"2402.02611","repositories_listed":0,"syntology":null},{"url":null,"slug":"sempool-simple-robust-and-interpretable-kg","title":"SemPool: Simple, robust, and interpretable KG pooling for enhancing language models","date":"2024-02-03","arxiv_id":"2402.02289","repositories_listed":0,"syntology":null},{"url":null,"slug":"bat-learning-to-reason-about-spatial-sounds","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01591","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-answers-reviewing-the-rationality","title":"LLMs May Perform MCQA by Selecting the Least Incorrect Option","date":"2024-02-02","arxiv_id":"2402.01349","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-prompt-caching-via-embedding","title":"Efficient Prompt Caching via Embedding Similarity","date":"2024-02-02","arxiv_id":"2402.01173","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-chain-of-thought-is-as-strong-as-its","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","date":"2024-02-01","arxiv_id":"2402.00559","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exam-based-evaluation-approach-beyond","title":"An Exam-based Evaluation Approach Beyond Traditional Relevance Judgments","date":"2024-02-01","arxiv_id":"2402.00309","repositories_listed":0,"syntology":null},{"url":null,"slug":"hiqa-a-hierarchical-contextual-augmentation","title":"HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA","date":"2024-02-01","arxiv_id":"2402.01767","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-generative-ai-systems-capable-of","title":"Can Generative AI Support Patients' & Caregivers' Informational Needs? Towards Task-Centric Evaluation Of AI Systems","date":"2024-01-31","arxiv_id":"2402.00234","repositories_listed":0,"syntology":null},{"url":null,"slug":"binding-touch-to-everything-learning-unified","title":"Binding Touch to Everything: Learning Unified Multimodal Tactile Representations","date":"2024-01-31","arxiv_id":"2401.18084","repositories_listed":0,"syntology":null},{"url":null,"slug":"desiderata-for-the-context-use-of-question","title":"Desiderata for the Context Use of Question Answering Systems","date":"2024-01-31","arxiv_id":"2401.18001","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-transformer-based-encoder-for","title":"Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks","date":"2024-01-30","arxiv_id":"2401.17396","repositories_listed":0,"syntology":null},{"url":null,"slug":"security-and-privacy-challenges-of-large","title":"Security and Privacy Challenges of Large Language Models: A Survey","date":"2024-01-30","arxiv_id":"2402.00888","repositories_listed":0,"syntology":null},{"url":null,"slug":"lcvo-an-efficient-pretraining-free-framework","title":"LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering","date":"2024-01-29","arxiv_id":"2401.15842","repositories_listed":0,"syntology":null},{"url":null,"slug":"muffin-or-chihuahua-challenging-large-vision","title":"Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA","date":"2024-01-29","arxiv_id":"2401.15847","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-optimizing-the-costs-of-llm-usage","title":"Towards Optimizing the Costs of LLM Usage","date":"2024-01-29","arxiv_id":"2402.01742","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-data-augmentation-for-robust-visual","title":"Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning","date":"2024-01-28","arxiv_id":"2401.15646","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-rag-based-question-answering-system","title":"A RAG-based Question Answering System Proposal for Understanding Islam: MufassirQAS LLM","date":"2024-01-27","arxiv_id":"2401.15378","repositories_listed":0,"syntology":null},{"url":null,"slug":"dataframe-qa-a-universal-llm-framework-on","title":"DataFrame QA: A Universal LLM Framework on DataFrame Question Answering Without Data Exposure","date":"2024-01-27","arxiv_id":"2401.15463","repositories_listed":0,"syntology":null}],"record_sha256":"c1fe361730bcc824ada19f6284d6ca85392a04e768c9b0f3bda0480fb3a33450","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}