{"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/53","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":53,"pages_in_order":109,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/task/question-answering/papers/54","papers":[{"url":null,"slug":"object-centric-temporal-consistency-via","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","date":"2024-10-21","arxiv_id":"2410.15728","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag4itops-a-supervised-fine-tunable-and","title":"RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance","date":"2024-10-21","arxiv_id":"2410.15805","repositories_listed":0,"syntology":null},{"url":null,"slug":"xgen-mm-vid-blip-3-video-you-only-need-32","title":"xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs","date":"2024-10-21","arxiv_id":"2410.16267","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-consistencies-in-llm-responses","title":"Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering","date":"2024-10-20","arxiv_id":"2410.15440","repositories_listed":0,"syntology":null},{"url":null,"slug":"chitrojera-a-regionally-relevant-visual","title":"ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla","date":"2024-10-19","arxiv_id":"2410.14991","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-highlighting-reducing","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","date":"2024-10-19","arxiv_id":"2410.15116","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-ultra-large-chinese-language-and-vision","title":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","date":"2024-10-19","arxiv_id":"2410.15074","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-blind-guessing-calibration-of","title":"Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models","date":"2024-10-18","arxiv_id":"2410.14248","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-training-inference-gap-in-llms","title":"Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens","date":"2024-10-18","arxiv_id":"2410.14655","repositories_listed":0,"syntology":null},{"url":null,"slug":"discograms-enhancing-movie-screen-play","title":"DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph","date":"2024-10-18","arxiv_id":"2410.14666","repositories_listed":0,"syntology":null},{"url":null,"slug":"e3d-gpt-enhanced-3d-visual-foundation-for","title":"E3D-GPT: Enhanced 3D Visual Foundation for Medical Vision-Language Model","date":"2024-10-18","arxiv_id":"2410.14200","repositories_listed":0,"syntology":null},{"url":null,"slug":"electrocardiogram-language-model-for-few-shot","title":"Electrocardiogram-Language Model for Few-Shot Question Answering with Meta Learning","date":"2024-10-18","arxiv_id":"2410.14464","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcsff-multi-modal-consistency-and-specificity","title":"MCSFF: Multi-modal Consistency and Specificity Fusion Framework for Entity Alignment","date":"2024-10-18","arxiv_id":"2410.14584","repositories_listed":0,"syntology":null},{"url":null,"slug":"naturalbench-evaluating-vision-language","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","date":"2024-10-18","arxiv_id":"2410.14669","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-retrieval-augmented-generation","title":"Optimizing Retrieval-Augmented Generation with Elasticsearch for Enhanced Question-Answering Systems","date":"2024-10-18","arxiv_id":"2410.14167","repositories_listed":0,"syntology":null},{"url":null,"slug":"ra-blip-multimodal-adaptive-retrieval","title":"RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training","date":"2024-10-18","arxiv_id":"2410.14154","repositories_listed":0,"syntology":null},{"url":null,"slug":"spfresh-incremental-in-place-update-for","title":"SPFresh: Incremental In-Place Update for Billion-Scale Vector Search","date":"2024-10-18","arxiv_id":"2410.14452","repositories_listed":0,"syntology":null},{"url":null,"slug":"swaquad-24-qa-benchmark-dataset-in-swahili","title":"SwaQuAD-24: QA Benchmark Dataset in Swahili","date":"2024-10-18","arxiv_id":"2410.14289","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-action-localization-via-the","title":"Zero-shot Action Localization via the Confidence of Large Vision-Language Models","date":"2024-10-18","arxiv_id":"2410.14340","repositories_listed":0,"syntology":null},{"url":null,"slug":"accounting-for-sycophancy-in-language-model","title":"Accounting for Sycophancy in Language Model Uncertainty Estimation","date":"2024-10-17","arxiv_id":"2410.14746","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaswitch-adaptive-switching-between-small","title":"AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning","date":"2024-10-17","arxiv_id":"2410.13181","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-large-language-model-attribution","title":"Advancing Large Language Model Attribution through Self-Improving","date":"2024-10-17","arxiv_id":"2410.13298","repositories_listed":0,"syntology":null},{"url":null,"slug":"bqa-body-language-question-answering-dataset","title":"BQA: Body Language Question Answering Dataset for Video Large Language Models","date":"2024-10-17","arxiv_id":"2410.13206","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-self-generated-documents-for","title":"Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models","date":"2024-10-17","arxiv_id":"2410.13192","repositories_listed":0,"syntology":null},{"url":null,"slug":"finqapt-empowering-financial-decisions-with","title":"FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipeline","date":"2024-10-17","arxiv_id":"2410.13959","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-isolated-conversations-to-hierarchical","title":"From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs","date":"2024-10-17","arxiv_id":"2410.14052","repositories_listed":0,"syntology":null},{"url":null,"slug":"rescueadi-adaptive-disaster-interpretation-in","title":"RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents","date":"2024-10-17","arxiv_id":"2410.13384","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automatic-and-cost-efficient-peer-review","title":"An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation","date":"2024-10-16","arxiv_id":"2410.12265","repositories_listed":0,"syntology":null},{"url":"/paper/developing-question-answering-models-in-low","slug":"developing-question-answering-models-in-low","title":"Developing Question-Answering Models in Low-Resource Languages: A Case Study on Turkish Medical Texts Using Transformer-Based Approaches","date":"2024-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-a-tool-for-mining","title":"Large Language Models as a Tool for Mining Object Knowledge","date":"2024-10-16","arxiv_id":"2410.12959","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-domain-question-answering-with","title":"Open Domain Question Answering with Conflicting Contexts","date":"2024-10-16","arxiv_id":"2410.12311","repositories_listed":0,"syntology":null},{"url":null,"slug":"pyramid-driven-alignment-pyramid-principle","title":"Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs","date":"2024-10-16","arxiv_id":"2410.12298","repositories_listed":0,"syntology":null},{"url":null,"slug":"refine-on-scarce-data-retrieval-enhancement","title":"REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models","date":"2024-10-16","arxiv_id":"2410.12890","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentigraph-an-interactive-knowledge-graph","title":"AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data","date":"2024-10-15","arxiv_id":"2410.11531","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-reasoning-in-large-language-models-a","title":"Causal Reasoning in Large Language Models: A Knowledge Graph Approach","date":"2024-10-15","arxiv_id":"2410.11588","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-users-in-digital-privacy","title":"Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents","date":"2024-10-15","arxiv_id":"2410.11906","repositories_listed":0,"syntology":null},{"url":null,"slug":"largepig-your-large-language-model-is","title":"LargePiG: Your Large Language Model is Secretly a Pointer Generator","date":"2024-10-15","arxiv_id":"2410.11366","repositories_listed":0,"syntology":null},{"url":null,"slug":"omcat-omni-context-aware-transformer","title":"OMCAT: Omni Context Aware Transformer","date":"2024-10-15","arxiv_id":"2410.12109","repositories_listed":0,"syntology":null},{"url":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","repositories_listed":0,"syntology":null},{"url":null,"slug":"telco-dpr-a-hybrid-dataset-for-evaluating","title":"Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specifications","date":"2024-10-15","arxiv_id":"2410.19790","repositories_listed":0,"syntology":null},{"url":null,"slug":"unleashing-the-power-of-llms-as-multi-modal","title":"Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data","date":"2024-10-15","arxiv_id":"2410.11235","repositories_listed":0,"syntology":null},{"url":null,"slug":"banglaquad-a-bengali-open-domain-question","title":"BanglaQuAD: A Bengali Open-domain Question Answering Dataset","date":"2024-10-14","arxiv_id":"2410.10229","repositories_listed":0,"syntology":null},{"url":null,"slug":"eliminating-the-language-bias-for-visual","title":"Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention","date":"2024-10-14","arxiv_id":"2410.10184","repositories_listed":0,"syntology":null},{"url":null,"slug":"flare-faithful-logic-aided-reasoning-and","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","date":"2024-10-14","arxiv_id":"2410.11900","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-step-towards-mixture-of-grader-statistical","title":"A Step Towards Mixture of Grader: Statistical Analysis of Existing Automatic Evaluation Metrics","date":"2024-10-13","arxiv_id":"2410.10030","repositories_listed":0,"syntology":null},{"url":null,"slug":"chartkg-a-knowledge-graph-based","title":"ChartKG: A Knowledge-Graph-Based Representation for Chart Images","date":"2024-10-13","arxiv_id":"2410.09761","repositories_listed":0,"syntology":null},{"url":null,"slug":"lore-logit-ranked-retriever-ensemble-for","title":"LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering","date":"2024-10-13","arxiv_id":"2410.10042","repositories_listed":0,"syntology":null},{"url":"/paper/mmcomposition-revisiting-the-compositionality","slug":"mmcomposition-revisiting-the-compositionality","title":"MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models","date":"2024-10-13","arxiv_id":"2410.09733","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-llava-toward-surgical-scenario","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","date":"2024-10-13","arxiv_id":"2410.09750","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-electronic-health-records-text","title":"Enhanced Electronic Health Records Text Summarization Using Large Language Models","date":"2024-10-12","arxiv_id":"2410.09628","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-video-language-foundation-models","title":"Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering","date":"2024-10-12","arxiv_id":"2410.09380","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-the-groundedness-of-legal-question","title":"Measuring the Groundedness of Legal Question-Answering Systems","date":"2024-10-11","arxiv_id":"2410.08764","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimized-biomedical-question-answering","title":"Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration","date":"2024-10-11","arxiv_id":"2410.12856","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-contextual-information-for-long","title":"Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision","date":"2024-10-11","arxiv_id":"2410.08623","repositories_listed":0,"syntology":null},{"url":null,"slug":"vit3d-alignment-of-llama3-3d-medical-image","title":"ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation","date":"2024-10-11","arxiv_id":"2410.08588","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-knowledge-graphs-make-large-language","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study over Open-ended Question Answering","date":"2024-10-10","arxiv_id":"2410.08085","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-you-know-what-you-are-talking-about","title":"Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation","date":"2024-10-10","arxiv_id":"2410.08320","repositories_listed":0,"syntology":null},{"url":null,"slug":"emerging-pixel-grounding-in-large-multimodal","title":"Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision","date":"2024-10-10","arxiv_id":"2410.08209","repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-the-difficulty-of-automatically","title":"Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference","date":"2024-10-10","arxiv_id":"2410.08289","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrag-bench-vision-centric-evaluation-for","title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models","date":"2024-10-10","arxiv_id":"2410.08182","repositories_listed":0,"syntology":null},{"url":null,"slug":"optima-optimizing-effectiveness-and","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","date":"2024-10-10","arxiv_id":"2410.08115","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewriting-conversational-utterances-with","title":"Rewriting Conversational Utterances with Instructed Large Language Models","date":"2024-10-10","arxiv_id":"2410.07797","repositories_listed":0,"syntology":null},{"url":null,"slug":"saka-an-intelligent-platform-for-semi","title":"SAKA: An Intelligent Platform for Semi-automated Knowledge Graph Construction and Application","date":"2024-10-10","arxiv_id":"2410.08094","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-then-identify-a-general-framework-for","title":"Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models","date":"2024-10-10","arxiv_id":"2410.08174","repositories_listed":0,"syntology":null},{"url":"/paper/tvbench-redesigning-video-language-evaluation","slug":"tvbench-redesigning-video-language-evaluation","title":"TVBench: Redesigning Video-Language Evaluation","date":"2024-10-10","arxiv_id":"2410.07752","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-great-minds-think-alike-investigating","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","date":"2024-10-09","arxiv_id":"2410.06524","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-multimodal-llm-for-detailed-and","title":"Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization","date":"2024-10-09","arxiv_id":"2410.06682","repositories_listed":0,"syntology":null},{"url":null,"slug":"fltlm-an-intergrated-long-context-large","title":"FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding","date":"2024-10-09","arxiv_id":"2410.06886","repositories_listed":0,"syntology":null},{"url":null,"slug":"personal-intelligence-system-unilm-hybrid-on","title":"Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara","date":"2024-10-09","arxiv_id":"2410.06973","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-replace-reduction-an-effective","title":"PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models","date":"2024-10-09","arxiv_id":"2410.07278","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-long-text-processing-with-short","title":"SEGMENT+: Long Text Processing with Short-Context Language Models","date":"2024-10-09","arxiv_id":"2410.06519","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-factor-level-preferences-to","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","date":"2024-10-09","arxiv_id":"2410.06965","repositories_listed":0,"syntology":null},{"url":null,"slug":"actionatlas-a-videoqa-benchmark-for-domain","title":"ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition","date":"2024-10-08","arxiv_id":"2410.05774","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-captioning-task-specific-prompting-for","title":"Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoning","date":"2024-10-08","arxiv_id":"2410.05928","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-discovery-in-e-commerce","title":"Information Discovery in e-Commerce","date":"2024-10-08","arxiv_id":"2410.05763","repositories_listed":0,"syntology":null},{"url":null,"slug":"portllm-personalizing-evolving-large-language","title":"PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches","date":"2024-10-08","arxiv_id":"2410.10870","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-reasoning-transfer-from-text-to","title":"Temporal Reasoning Transfer from Text to Video","date":"2024-10-08","arxiv_id":"2410.06166","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-level-causal-relation-extraction","title":"Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering","date":"2024-10-07","arxiv_id":"2410.04752","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-equity-in-large-language-models-for","title":"Mitigating the Risk of Health Inequity Exacerbated by Large Language Models","date":"2024-10-07","arxiv_id":"2410.05180","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-r-3-on-in-consistency-of-multi-modal-large","title":"MM-R$^3$: On (In-)Consistency of Multi-modal Large Language Models (MLLMs)","date":"2024-10-07","arxiv_id":"2410.04778","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-model-benchmarking-with-only-a-few","title":"Precise Model Benchmarking with Only a Few Observations","date":"2024-10-07","arxiv_id":"2410.05222","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm2vec-training-vision-language-models-for","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","date":"2024-10-07","arxiv_id":"2410.05160","repositories_listed":0,"syntology":null},{"url":"/paper/adaptive-question-answering-enhancing","slug":"adaptive-question-answering-enhancing","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","date":"2024-10-05","arxiv_id":"2410.04241","repositories_listed":0,"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":3,"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/adaptive-question-answering-enhancing#ran","syntology_url":"https://syntology.ai/paper/2410.04241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04241"}},"official":null}},{"url":null,"slug":"beyond-forecasting-compositional-time-series","title":"Beyond Forecasting: Compositional Time Series Reasoning for End-to-End Task Execution","date":"2024-10-05","arxiv_id":"2410.04047","repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-of-factify5wqa-fact-verification","title":"Overview of Factify5WQA: Fact Verification through 5W Question-Answering","date":"2024-10-05","arxiv_id":"2410.04236","repositories_listed":0,"syntology":null},{"url":null,"slug":"alr-2-a-retrieve-then-reason-framework-for","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","date":"2024-10-04","arxiv_id":"2410.03227","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-for-automatic-question","title":"Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages","date":"2024-10-04","arxiv_id":"2410.03197","repositories_listed":0,"syntology":null},{"url":null,"slug":"frame-voyager-learning-to-query-frames-for","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","date":"2024-10-04","arxiv_id":"2410.03226","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-semantic-structure-through-first","title":"Learning Semantic Structure through First-Order-Logic Translation","date":"2024-10-04","arxiv_id":"2410.03203","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-answering-system-for-bangla-fine","title":"Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain","date":"2024-10-04","arxiv_id":"2410.03923","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-list-grounded-question-answering","title":"Structured List-Grounded Question Answering","date":"2024-10-04","arxiv_id":"2410.03950","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-of-retrieval-augmented","title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","date":"2024-10-03","arxiv_id":"2410.12837","repositories_listed":0,"syntology":null},{"url":null,"slug":"coal-mining-question-answering-with-llms","title":"Coal Mining Question Answering with LLMs","date":"2024-10-03","arxiv_id":"2410.02959","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-an-end-to-end-voice-assistant","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","date":"2024-10-03","arxiv_id":"2410.02678","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-specific-retrieval-augmented","title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","date":"2024-10-03","arxiv_id":"2410.02721","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-large-language-models-in-embodied","title":"Grounding Large Language Models In Embodied Environment With Imperfect World Models","date":"2024-10-03","arxiv_id":"2410.02742","repositories_listed":0,"syntology":null},{"url":null,"slug":"listening-to-the-wise-few-select-and-copy","title":"Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA","date":"2024-10-03","arxiv_id":"2410.02343","repositories_listed":0,"syntology":null},{"url":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-structured-thinking-in-language","title":"Unlocking Structured Thinking in Language Models with Cognitive Prompting","date":"2024-10-03","arxiv_id":"2410.02953","repositories_listed":0,"syntology":null},{"url":"/paper/video-instruction-tuning-with-synthetic-data","slug":"video-instruction-tuning-with-synthetic-data","title":"Video Instruction Tuning With Synthetic Data","date":"2024-10-03","arxiv_id":"2410.02713","repositories_listed":0,"syntology":null}],"record_sha256":"aca6ca8250e0189becfd96d3c1fc555354b81ccce43bd2e151174cac66088675","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}