{"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/48","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":48,"pages_in_order":109,"rows_per_page":100,"rows":[4701,4800],"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/47","next":"/task/question-answering/papers/49","papers":[{"url":null,"slug":"time-mqa-time-series-multi-task-question","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","date":"2025-02-26","arxiv_id":"2503.01875","repositories_listed":0,"syntology":null},{"url":null,"slug":"winning-big-with-small-models-knowledge","title":"Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents","date":"2025-02-26","arxiv_id":"2502.19545","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-knowledge-boundary-of-vision-large","title":"Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference","date":"2025-02-25","arxiv_id":"2502.18023","repositories_listed":0,"syntology":null},{"url":null,"slug":"filterrag-zero-shot-informed-retrieval","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","date":"2025-02-25","arxiv_id":"2502.18536","repositories_listed":0,"syntology":null},{"url":null,"slug":"kirag-knowledge-driven-iterative-retriever","title":"KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation","date":"2025-02-25","arxiv_id":"2502.18397","repositories_listed":0,"syntology":null},{"url":null,"slug":"say-less-mean-more-leveraging-pragmatics-in","title":"Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation","date":"2025-02-25","arxiv_id":"2502.17839","repositories_listed":0,"syntology":null},{"url":null,"slug":"secura-sigmoid-enhanced-cur-decomposition","title":"SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models","date":"2025-02-25","arxiv_id":"2502.18168","repositories_listed":0,"syntology":null},{"url":null,"slug":"aad-llm-neural-attention-driven-auditory","title":"AAD-LLM: Neural Attention-Driven Auditory Scene Understanding","date":"2025-02-24","arxiv_id":"2502.16794","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-in-one-understanding-and-generation-in","title":"All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark","date":"2025-02-24","arxiv_id":"2502.16989","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-effect-of-retrieval","title":"Evaluating the Effect of Retrieval Augmentation on Social Biases","date":"2025-02-24","arxiv_id":"2502.17611","repositories_listed":0,"syntology":null},{"url":null,"slug":"mqadet-a-plug-and-play-paradigm-for-enhancing","title":"MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering","date":"2025-02-23","arxiv_id":"2502.16486","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-visual-question-answering-1","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","date":"2025-02-23","arxiv_id":"2502.16641","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracking-the-copyright-of-large-vision","title":"Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images","date":"2025-02-23","arxiv_id":"2502.16593","repositories_listed":0,"syntology":null},{"url":null,"slug":"echo-a-large-language-model-with-temporal","title":"Echo: A Large Language Model with Temporal Episodic Memory","date":"2025-02-22","arxiv_id":"2502.16090","repositories_listed":0,"syntology":null},{"url":null,"slug":"eperm-an-evidence-path-enhanced-reasoning","title":"EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering","date":"2025-02-22","arxiv_id":"2502.16171","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-fusion-an-ensemble","title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models","date":"2025-02-22","arxiv_id":"2503.05757","repositories_listed":0,"syntology":null},{"url":null,"slug":"chats-grid-an-iterative-retrieval-q-a","title":"Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid","date":"2025-02-21","arxiv_id":"2502.15583","repositories_listed":0,"syntology":null},{"url":null,"slug":"directional-gradient-projection-for-robust","title":"Directional Gradient Projection for Robust Fine-Tuning of Foundation Models","date":"2025-02-21","arxiv_id":"2502.15895","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-llms-with-logical-reasoning-a","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","date":"2025-02-21","arxiv_id":"2502.15652","repositories_listed":0,"syntology":null},{"url":null,"slug":"mhqa-a-diverse-knowledge-intensive-mental","title":"MHQA: A Diverse, Knowledge Intensive Mental Health Question Answering Challenge for Language Models","date":"2025-02-21","arxiv_id":"2502.15418","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-the-gap-static-and-interactive","title":"Mind the Gap! Static and Interactive Evaluations of Large Audio Models","date":"2025-02-21","arxiv_id":"2502.15919","repositories_listed":0,"syntology":null},{"url":null,"slug":"superintelligent-agents-pose-catastrophic","title":"Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?","date":"2025-02-21","arxiv_id":"2502.15657","repositories_listed":0,"syntology":null},{"url":null,"slug":"transmamba-fast-universal-architecture","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","date":"2025-02-21","arxiv_id":"2502.15130","repositories_listed":0,"syntology":null},{"url":null,"slug":"argument-based-comparative-question-answering","title":"Argument-Based Comparative Question Answering Evaluation Benchmark","date":"2025-02-20","arxiv_id":"2502.14476","repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-prompt-length-on-domain-specific","title":"Effects of Prompt Length on Domain-specific Tasks for Large Language Models","date":"2025-02-20","arxiv_id":"2502.14255","repositories_listed":0,"syntology":null},{"url":null,"slug":"epman-episodic-memory-attention-for","title":"EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts","date":"2025-02-20","arxiv_id":"2502.14280","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-advanced-techniques-for-visual","title":"Exploring Advanced Techniques for Visual Question Answering: A Comprehensive Comparison","date":"2025-02-20","arxiv_id":"2502.14827","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-relevance-propagated-from-retriever-to","title":"Is Relevance Propagated from Retriever to Generator in RAG?","date":"2025-02-20","arxiv_id":"2502.15025","repositories_listed":0,"syntology":null},{"url":null,"slug":"medhallu-a-comprehensive-benchmark-for","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models","date":"2025-02-20","arxiv_id":"2502.14302","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-lost-in-retrieval-problems-in","title":"Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering","date":"2025-02-20","arxiv_id":"2502.14245","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlp-akg-few-shot-construction-of-nlp-academic","title":"NLP-AKG: Few-Shot Construction of NLP Academic Knowledge Graph Based on LLM","date":"2025-02-20","arxiv_id":"2502.14192","repositories_listed":0,"syntology":null},{"url":null,"slug":"triangulating-llm-progress-through-benchmarks","title":"Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests","date":"2025-02-20","arxiv_id":"2502.14359","repositories_listed":0,"syntology":null},{"url":null,"slug":"dh-rag-a-dynamic-historical-context-powered","title":"DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue","date":"2025-02-19","arxiv_id":"2502.13847","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcts-kbqa-monte-carlo-tree-search-for","title":"MCTS-KBQA: Monte Carlo Tree Search for Knowledge Base Question Answering","date":"2025-02-19","arxiv_id":"2502.13428","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-semantic-relations-challenges-for","title":"Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning","date":"2025-02-19","arxiv_id":"2502.14086","repositories_listed":0,"syntology":null},{"url":null,"slug":"priv-qa-privacy-preserving-question-answering","title":"PRIV-QA: Privacy-Preserving Question Answering for Cloud Large Language Models","date":"2025-02-19","arxiv_id":"2502.13564","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-memorization-and-retriever","title":"Quantifying Memorization and Retriever Performance in Retrieval-Augmented Vision-Language Models","date":"2025-02-19","arxiv_id":"2502.13836","repositories_listed":0,"syntology":null},{"url":null,"slug":"refind-retrieval-augmented-factuality","title":"REFIND: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models","date":"2025-02-19","arxiv_id":"2502.13622","repositories_listed":0,"syntology":null},{"url":null,"slug":"rgar-recurrence-generation-augmented","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","date":"2025-02-19","arxiv_id":"2502.13361","repositories_listed":0,"syntology":null},{"url":null,"slug":"sce2drivex-a-generalized-mllm-framework-for","title":"Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning","date":"2025-02-19","arxiv_id":"2502.14917","repositories_listed":0,"syntology":null},{"url":null,"slug":"tabsd-large-free-form-table-question","title":"TabSD: Large Free-Form Table Question Answering with SQL-Based Table Decomposition","date":"2025-02-19","arxiv_id":"2502.13422","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-adaptive-memory-based-optimization","title":"Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation","date":"2025-02-19","arxiv_id":"2504.05312","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-of-these-best-describes-multiple-choice","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","date":"2025-02-19","arxiv_id":"2502.14127","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-knowledge-graphs-enhance-medical","title":"Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge","date":"2025-02-18","arxiv_id":"2502.13010","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-profile-from-surface-level-facts-to","title":"Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs","date":"2025-02-18","arxiv_id":"2502.12988","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-llm-reasoning-with-knowledge-graphs","title":"Grounding LLM Reasoning with Knowledge Graphs","date":"2025-02-18","arxiv_id":"2502.13247","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-clinical-question-answering-with","title":"Improving Clinical Question Answering with Multi-Task Learning: A Joint Approach for Answer Extraction and Medical Categorization","date":"2025-02-18","arxiv_id":"2502.13108","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-european-language-models","title":"Multilingual European Language Models: Benchmarking Approaches and Challenges","date":"2025-02-18","arxiv_id":"2502.12895","repositories_listed":0,"syntology":null},{"url":null,"slug":"savaal-scalable-concept-driven-question","title":"Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning","date":"2025-02-18","arxiv_id":"2502.12477","repositories_listed":0,"syntology":null},{"url":null,"slug":"searchrag-can-search-engines-be-helpful-for","title":"SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?","date":"2025-02-18","arxiv_id":"2502.13233","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplevqa-multimodal-factuality-evaluation","title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models","date":"2025-02-18","arxiv_id":"2502.13059","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-automated-workflow-in-materials","title":"Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language models","date":"2025-02-18","arxiv_id":"2502.14904","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm-agents-for-coordinating-multi-user","title":"LM Agents for Coordinating Multi-User Information Gathering","date":"2025-02-17","arxiv_id":"2502.12328","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-retrieval-augmentation-for-open","title":"Multi-Modal Retrieval Augmentation for Open-Ended and Knowledge-Intensive Video Question Answering","date":"2025-02-17","arxiv_id":"2502.11747","repositories_listed":0,"syntology":null},{"url":null,"slug":"ontology-guided-reverse-thinking-makes-large","title":"Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering","date":"2025-02-17","arxiv_id":"2502.11491","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-vs-graphrag-a-systematic-evaluation-and","title":"RAG vs. GraphRAG: A Systematic Evaluation and Key Insights","date":"2025-02-17","arxiv_id":"2502.11371","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-the-world-discover-knowledge-a-chinese","title":"\"See the World, Discover Knowledge\": A Chinese Factuality Evaluation for Large Vision Language Models","date":"2025-02-17","arxiv_id":"2502.11718","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-geometry-of-bert","title":"The geometry of BERT","date":"2025-02-17","arxiv_id":"2502.12033","repositories_listed":0,"syntology":null},{"url":null,"slug":"quote-question-oriented-text-embeddings","title":"QuOTE: Question-Oriented Text Embeddings","date":"2025-02-16","arxiv_id":"2502.10976","repositories_listed":0,"syntology":null},{"url":null,"slug":"roserag-robust-retrieval-augmented-generation","title":"RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization","date":"2025-02-16","arxiv_id":"2502.10993","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-rotary-position-embedding-may-cause","title":"The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval","date":"2025-02-16","arxiv_id":"2502.11276","repositories_listed":0,"syntology":null},{"url":null,"slug":"vendi-rag-adaptively-trading-off-diversity","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","date":"2025-02-16","arxiv_id":"2502.11228","repositories_listed":0,"syntology":null},{"url":null,"slug":"k-edit-language-model-editing-with-contextual","title":"K-Edit: Language Model Editing with Contextual Knowledge Awareness","date":"2025-02-15","arxiv_id":"2502.10626","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-meta-and-object-level","title":"Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering","date":"2025-02-14","arxiv_id":"2502.10338","repositories_listed":0,"syntology":null},{"url":null,"slug":"insect-foundation-a-foundation-model-and-1","title":"Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding","date":"2025-02-14","arxiv_id":"2502.09906","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-an-llm-for-rag-train-on-self","title":"Post-training an LLM for RAG? Train on Self-Generated Demonstrations","date":"2025-02-14","arxiv_id":"2502.10596","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2v-llm-vehicle-to-vehicle-cooperative","title":"V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multi-Modal Large Language Models","date":"2025-02-14","arxiv_id":"2502.09980","repositories_listed":0,"syntology":null},{"url":null,"slug":"abduction-of-domain-relationships-from-data","title":"Abduction of Domain Relationships from Data for VQA","date":"2025-02-13","arxiv_id":"2502.09219","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-english-the-impact-of-prompt","title":"Beyond English: The Impact of Prompt Translation Strategies across Languages and Tasks in Multilingual LLMs","date":"2025-02-13","arxiv_id":"2502.09331","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-enhances-an-llm-s-performance-in","title":"Diversity Enhances an LLM's Performance in RAG and Long-context Task","date":"2025-02-13","arxiv_id":"2502.09017","repositories_listed":0,"syntology":null},{"url":null,"slug":"emoassist-emotional-assistant-for-visual","title":"EmoAssist: Emotional Assistant for Visual Impairment Community","date":"2025-02-13","arxiv_id":"2502.09285","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-tcm-question-answering-through-tree","title":"Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs","date":"2025-02-13","arxiv_id":"2502.09156","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-graph-question-answering-with-asp-and","title":"Visual Graph Question Answering with ASP and LLMs for Language Parsing","date":"2025-02-13","arxiv_id":"2502.09211","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-mechanistic-circuits-for-extractive","title":"On Mechanistic Circuits for Extractive Question-Answering","date":"2025-02-12","arxiv_id":"2502.08059","repositories_listed":0,"syntology":null},{"url":null,"slug":"foqa-a-faroese-question-answering-dataset","title":"FoQA: A Faroese Question-Answering Dataset","date":"2025-02-11","arxiv_id":"2502.07642","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-language-models-robust-against","title":"Making Language Models Robust Against Negation","date":"2025-02-11","arxiv_id":"2502.07717","repositories_listed":0,"syntology":null},{"url":null,"slug":"retreever-tree-based-coarse-to-fine","title":"ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval","date":"2025-02-11","arxiv_id":"2502.07971","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-for-edge-networks-a","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","date":"2025-02-11","arxiv_id":"2502.07855","repositories_listed":0,"syntology":null},{"url":null,"slug":"2502-06659","title":"Who Taught You That? Tracing Teachers in Model Distillation","date":"2025-02-10","arxiv_id":"2502.06659","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-distribution-prediction-a-unified","title":"Generative Distribution Prediction: A Unified Approach to Multimodal Learning","date":"2025-02-10","arxiv_id":"2502.07090","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-musical-representations-for-music","title":"Learning Musical Representations for Music Performance Question Answering","date":"2025-02-10","arxiv_id":"2502.06710","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-analysis-of-traditional-vqa","title":"Performance Analysis of Traditional VQA Models Under Limited Computational Resources","date":"2025-02-09","arxiv_id":"2502.05738","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-large-language-models-for-tool","title":"Self-Training Large Language Models for Tool-Use Without Demonstrations","date":"2025-02-09","arxiv_id":"2502.05867","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-llms-self-refinement-capability-via","title":"Evolving LLMs' Self-Refinement Capability via Iterative Preference Optimization","date":"2025-02-08","arxiv_id":"2502.05605","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-knowledge-feeding-to-language","title":"Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecture","date":"2025-02-07","arxiv_id":"2502.05233","repositories_listed":0,"syntology":null},{"url":null,"slug":"hummingbird-high-fidelity-image-generation","title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","date":"2025-02-07","arxiv_id":"2502.05153","repositories_listed":0,"syntology":null},{"url":null,"slug":"eclair-extracting-content-and-layout-with","title":"Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents","date":"2025-02-06","arxiv_id":"2502.04223","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-few-shot-continual-learning-in","title":"Efficient Few-Shot Continual Learning in Vision-Language Models","date":"2025-02-06","arxiv_id":"2502.04098","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-to-support-a-domain-specific-knowledge","title":"LLMs to Support a Domain Specific Knowledge Assistant","date":"2025-02-06","arxiv_id":"2502.04095","repositories_listed":0,"syntology":null},{"url":null,"slug":"terraq-spatiotemporal-question-answering-on","title":"TerraQ: Spatiotemporal Question-Answering on Satellite Image Archives","date":"2025-02-06","arxiv_id":"2502.04415","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-be-easily-confused-by-instructional","title":"LLMs can be easily Confused by Instructional Distractions","date":"2025-02-05","arxiv_id":"2502.04362","repositories_listed":0,"syntology":null},{"url":null,"slug":"sensorchat-answering-qualitative-and","title":"SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions","date":"2025-02-05","arxiv_id":"2502.02883","repositories_listed":0,"syntology":null},{"url":null,"slug":"amasquad-a-benchmark-for-amharic-extractive","title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering","date":"2025-02-04","arxiv_id":"2502.02047","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-spatial-language-grounding-through","title":"Exploring Spatial Language Grounding Through Referring Expressions","date":"2025-02-04","arxiv_id":"2502.04359","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-rag-spatial-retrieval-augmented","title":"Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions","date":"2025-02-04","arxiv_id":"2502.18470","repositories_listed":0,"syntology":null},{"url":null,"slug":"chartcitor-multi-agent-framework-for-fine","title":"ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution","date":"2025-02-03","arxiv_id":"2502.00989","repositories_listed":0,"syntology":null},{"url":null,"slug":"memento-no-more-coaching-ai-agents-to-master","title":"Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization","date":"2025-02-03","arxiv_id":"2502.01562","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-fliprag-topic-orientated-adversarial","title":"Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models","date":"2025-02-03","arxiv_id":"2502.01386","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypo3d-exploring-hypothetical-reasoning-in-3d","title":"Hypo3D: Exploring Hypothetical Reasoning in 3D","date":"2025-02-02","arxiv_id":"2502.00954","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-assisted-continual-learning-for-visual","title":"VLM-Assisted Continual learning for Visual Question Answering in Self-Driving","date":"2025-02-02","arxiv_id":"2502.00843","repositories_listed":0,"syntology":null}],"record_sha256":"b9e915b419d76aa716b1eb22ef33c19177d3f57b1dce2a2ce9225e3e59d5bcb5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}