{"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/60","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":60,"pages_in_order":109,"rows_per_page":100,"rows":[5901,6000],"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/59","next":"/task/question-answering/papers/61","papers":[{"url":null,"slug":"learning-to-plan-and-generate-text-with","title":"Learning to Plan and Generate Text with Citations","date":"2024-04-04","arxiv_id":"2404.03381","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-llm-hallucinations-via-conformal","title":"Mitigating LLM Hallucinations via Conformal Abstention","date":"2024-04-04","arxiv_id":"2405.01563","repositories_listed":0,"syntology":null},{"url":null,"slug":"probelm-plausibility-ranking-evaluation-for","title":"PRobELM: Plausibility Ranking Evaluation for Language Models","date":"2024-04-04","arxiv_id":"2404.03818","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-death-of-feature-engineering-bert-with","title":"The Death of Feature Engineering? BERT with Linguistic Features on SQuAD 2.0","date":"2024-04-04","arxiv_id":"2404.03184","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinyvqa-compact-multimodal-deep-neural","title":"TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices","date":"2024-04-04","arxiv_id":"2404.03574","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-prompt-selection-for-large-language","title":"Automatic Prompt Selection for Large Language Models","date":"2024-04-03","arxiv_id":"2404.02717","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-human-computer-interaction-in-chest","title":"Enhancing Human-Computer Interaction in Chest X-ray Analysis using Vision and Language Model with Eye Gaze Patterns","date":"2024-04-03","arxiv_id":"2404.02370","repositories_listed":0,"syntology":null},{"url":null,"slug":"mchartqa-a-universal-benchmark-for-multimodal","title":"mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning","date":"2024-04-02","arxiv_id":"2404.01548","repositories_listed":0,"syntology":null},{"url":"/paper/self-improvement-programming-for-temporal","slug":"self-improvement-programming-for-temporal","title":"Self-Improvement Programming for Temporal Knowledge Graph Question Answering","date":"2024-04-02","arxiv_id":"2404.01720","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-generalization-in-open-domain","title":"Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization","date":"2024-04-02","arxiv_id":"2404.01652","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-large-language-models-to-understand","title":"Using Large Language Models to Understand Telecom Standards","date":"2024-04-02","arxiv_id":"2404.02929","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect2interact-localizing-object-key-field","title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs","date":"2024-04-01","arxiv_id":"2404.01151","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-code-technical-report","title":"Stable Code Technical Report","date":"2024-04-01","arxiv_id":"2404.01226","repositories_listed":0,"syntology":null},{"url":null,"slug":"videodistill-language-aware-vision","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","date":"2024-04-01","arxiv_id":"2404.00973","repositories_listed":0,"syntology":null},{"url":null,"slug":"docmaster-a-unified-platform-for-annotation","title":"DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering","date":"2024-03-30","arxiv_id":"2404.00439","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-hop-question-answering-under-temporal","title":"Multi-hop Question Answering under Temporal Knowledge Editing","date":"2024-03-30","arxiv_id":"2404.00492","repositories_listed":0,"syntology":null},{"url":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-bias-in-large-vision-language","title":"Uncovering Bias in Large Vision-Language Models with Counterfactuals","date":"2024-03-29","arxiv_id":"2404.00166","repositories_listed":0,"syntology":null},{"url":null,"slug":"ethiomt-parallel-corpus-for-low-resource","title":"EthioMT: Parallel Corpus for Low-resource Ethiopian Languages","date":"2024-03-28","arxiv_id":"2403.19365","repositories_listed":0,"syntology":null},{"url":null,"slug":"mfort-qa-multi-hop-few-shot-open-rich-table","title":"MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering","date":"2024-03-28","arxiv_id":"2403.19116","repositories_listed":0,"syntology":null},{"url":null,"slug":"transparent-and-clinically-interpretable-ai","title":"Leveraging Expert Input for Robust and Explainable AI-Assisted Lung Cancer Detection in Chest X-rays","date":"2024-03-28","arxiv_id":"2403.19444","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-conversational-question-answering","title":"Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check","date":"2024-03-27","arxiv_id":"2403.18243","repositories_listed":0,"syntology":null},{"url":null,"slug":"malbert-is-a-compact-multilingual-bert-model","title":"mALBERT: Is a Compact Multilingual BERT Model Still Worth It?","date":"2024-03-27","arxiv_id":"2403.18338","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-gaze-grounded-visual-question-answering","title":"A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions","date":"2024-03-26","arxiv_id":"2403.17545","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpts-and-language-barrier-a-cross-lingual","title":"GPTs and Language Barrier: A Cross-Lingual Legal QA Examination","date":"2024-03-26","arxiv_id":"2403.18098","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-hallucination-definition","title":"Visual Hallucination: Definition, Quantification, and Prescriptive Remediations","date":"2024-03-26","arxiv_id":"2403.17306","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-it-vivid-dressing-your-animatable-biped","title":"Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text","date":"2024-03-25","arxiv_id":"2403.16897","repositories_listed":0,"syntology":null},{"url":null,"slug":"proptest-automatic-property-testing-for","title":"PropTest: Automatic Property Testing for Improved Visual Programming","date":"2024-03-25","arxiv_id":"2403.16921","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesize-step-by-step-tools-templates-and","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","date":"2024-03-25","arxiv_id":"2403.16385","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-agnostic-detector-for-insertion-based","title":"Task-Agnostic Detector for Insertion-Based Backdoor Attacks","date":"2024-03-25","arxiv_id":"2403.17155","repositories_listed":0,"syntology":null},{"url":null,"slug":"cbt-llm-a-chinese-large-language-model-for","title":"CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering","date":"2024-03-24","arxiv_id":"2403.16008","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-until-confident-efficient-exploration","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","date":"2024-03-23","arxiv_id":"2403.15941","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-retrieval-for-rag-based-question","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","date":"2024-03-23","arxiv_id":"2404.07221","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-instruct-llms-an-extraction-and-editing","title":"General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing","date":"2024-03-23","arxiv_id":"2403.15736","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrc-based-nested-medical-ner-with-co","title":"MRC-based Nested Medical NER with Co-prediction and Adaptive Pre-training","date":"2024-03-23","arxiv_id":"2403.15800","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-review-fusion-in-context","title":"Multi-Review Fusion-in-Context","date":"2024-03-22","arxiv_id":"2403.15351","repositories_listed":0,"syntology":null},{"url":null,"slug":"sphere-neural-networks-for-rational-reasoning","title":"Sphere Neural-Networks for Rational Reasoning","date":"2024-03-22","arxiv_id":"2403.15297","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-lvlm-learning-to-adapt-large-vision","title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","date":"2024-03-22","arxiv_id":"2405.10948","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-quality-matters-in-training-fusion-in","title":"Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering","date":"2024-03-21","arxiv_id":"2403.14197","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-emotion-phrases-from-tweets-using","title":"Extracting Emotion Phrases from Tweets using BART","date":"2024-03-21","arxiv_id":"2403.14050","repositories_listed":0,"syntology":null},{"url":null,"slug":"fit-rag-black-box-rag-with-factual","title":"FIT-RAG: Black-Box RAG with Factual Information and Token Reduction","date":"2024-03-21","arxiv_id":"2403.14374","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtbls-generating-tables-from-text-by","title":"gTBLS: Generating Tables from Text by Conditional Question Answering","date":"2024-03-21","arxiv_id":"2403.14457","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-multi-choice","title":"Large Language Models for Multi-Choice Question Classification of Medical Subjects","date":"2024-03-21","arxiv_id":"2403.14582","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-extraction-of-contradictions-from","title":"LLM-based Extraction of Contradictions from Patents","date":"2024-03-21","arxiv_id":"2403.14258","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-explanations-for-generative","title":"Multi-Level Explanations for Generative Language Models","date":"2024-03-21","arxiv_id":"2403.14459","repositories_listed":0,"syntology":null},{"url":null,"slug":"myvlm-personalizing-vlms-for-user-specific","title":"MyVLM: Personalizing VLMs for User-Specific Queries","date":"2024-03-21","arxiv_id":"2403.14599","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-distillation-for-open-ended-video","title":"Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels","date":"2024-03-21","arxiv_id":"2403.14430","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-baselines-for-data-efficient","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","date":"2024-03-20","arxiv_id":"2403.13499","repositories_listed":0,"syntology":null},{"url":null,"slug":"paramanu-ayn-an-efficient-novel-generative","title":"PARAMANU-AYN: Pretrain from scratch or Continual Pretraining of LLMs for Legal Domain Adaptation?","date":"2024-03-20","arxiv_id":"2403.13681","repositories_listed":0,"syntology":null},{"url":null,"slug":"polaris-a-safety-focused-llm-constellation","title":"Polaris: A Safety-focused LLM Constellation Architecture for Healthcare","date":"2024-03-20","arxiv_id":"2403.13313","repositories_listed":0,"syntology":null},{"url":null,"slug":"vi-mistral-x-building-a-vietnamese-language","title":"Vi-Mistral-X: Building a Vietnamese Language Model with Advanced Continual Pre-training","date":"2024-03-20","arxiv_id":"2403.15470","repositories_listed":0,"syntology":null},{"url":null,"slug":"as-firm-as-their-foundations-can-open-sourced","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","date":"2024-03-19","arxiv_id":"2403.12693","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-question-answering","title":"Towards Unsupervised Question Answering System with Multi-level Summarization for Legal Text","date":"2024-03-19","arxiv_id":"2403.13107","repositories_listed":0,"syntology":null},{"url":null,"slug":"wolf-large-language-model-framework-for-cxr","title":"WoLF: Wide-scope Large Language Model Framework for CXR Understanding","date":"2024-03-19","arxiv_id":"2403.15456","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-generate-human-like-wayfinding","title":"Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis","date":"2024-03-18","arxiv_id":"2403.11487","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexcap-generating-rich-localized-and","title":"FlexCap: Describe Anything in Images in Controllable Detail","date":"2024-03-18","arxiv_id":"2403.12026","repositories_listed":0,"syntology":null},{"url":"/paper/scene-llm-extending-language-model-for-3d","slug":"scene-llm-extending-language-model-for-3d","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","date":"2024-03-18","arxiv_id":"2403.11401","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-imagine-plan-discovering-and","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","date":"2024-03-18","arxiv_id":"2403.13438","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-event-causality-identification-with","title":"Enhancing Event Causality Identification with Rationale and Structure-Aware Causal Question Answering","date":"2024-03-17","arxiv_id":"2403.11129","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-vqa-with-frozen-llms-a-tale-of-two","title":"Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches","date":"2024-03-17","arxiv_id":"2403.11317","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowmind-automatic-workflow-generation-with","title":"FlowMind: Automatic Workflow Generation with LLMs","date":"2024-03-17","arxiv_id":"2404.13050","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-a-gpt4-powered-ai-agent-be-a-good-enough","title":"Can a GPT4-Powered AI Agent Be a Good Enough Performance Attribution Analyst?","date":"2024-03-15","arxiv_id":"2403.10482","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-image-classification-and","title":"Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models","date":"2024-03-15","arxiv_id":"2403.10287","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-condensation-and-reasoning-for","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","date":"2024-03-15","arxiv_id":"2403.10037","repositories_listed":0,"syntology":null},{"url":null,"slug":"lost-in-overlap-exploring-watermark-collision","title":"Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs","date":"2024-03-15","arxiv_id":"2403.10020","repositories_listed":0,"syntology":null},{"url":null,"slug":"perl-parameter-efficient-reinforcement","title":"Parameter Efficient Reinforcement Learning from Human Feedback","date":"2024-03-15","arxiv_id":"2403.10704","repositories_listed":0,"syntology":null},{"url":null,"slug":"helpful-or-harmful-exploring-the-efficacy-of","title":"Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention","date":"2024-03-14","arxiv_id":"2403.09795","repositories_listed":0,"syntology":null},{"url":null,"slug":"proswitch-knowledge-guided-language-model","title":"ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses","date":"2024-03-14","arxiv_id":"2403.09131","repositories_listed":0,"syntology":null},{"url":null,"slug":"visiongpt-vision-language-understanding-agent","title":"VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework","date":"2024-03-14","arxiv_id":"2403.09027","repositories_listed":0,"syntology":null},{"url":null,"slug":"tina-think-interaction-and-action-framework","title":"TINA: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation","date":"2024-03-13","arxiv_id":"2403.08833","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-interface-for-adversarial-trivia","title":"A novel interface for adversarial trivia question-writing","date":"2024-03-12","arxiv_id":"2404.00011","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-large-language-models-with","title":"Fine-tuning Large Language Models with Sequential Instructions","date":"2024-03-12","arxiv_id":"2403.07794","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-the-impact-of-attribute-editing-on","title":"Mitigating the Impact of Attribute Editing on Face Recognition","date":"2024-03-12","arxiv_id":"2403.08092","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-generative-large-language-model","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","date":"2024-03-12","arxiv_id":"2403.07872","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-instructions-to-constraints-language","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","date":"2024-03-10","arxiv_id":"2403.06326","repositories_listed":0,"syntology":null},{"url":null,"slug":"mp2d-an-automated-topic-shift-dialogue","title":"MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs","date":"2024-03-09","arxiv_id":"2403.05814","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatasu-evoking-llm-s-reflexion-to-truly","title":"ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues","date":"2024-03-08","arxiv_id":"2403.05326","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-biomedical-text-mining-with","title":"Advancing Chinese biomedical text mining with community challenges","date":"2024-03-07","arxiv_id":"2403.04261","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-assessment-of-recent-large","title":"Effectiveness Assessment of Recent Large Vision-Language Models","date":"2024-03-07","arxiv_id":"2403.04306","repositories_listed":0,"syntology":null},{"url":null,"slug":"snapntell-enhancing-entity-centric-visual","title":"SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM","date":"2024-03-07","arxiv_id":"2403.04735","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-and-flexible-multi-concept-parsing","title":"A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching","date":"2024-03-05","arxiv_id":"2403.02975","repositories_listed":0,"syntology":null},{"url":null,"slug":"clevr-poc-reasoning-intensive-visual-question","title":"CLEVR-POC: Reasoning-Intensive Visual Question Answering in Partially Observable Environments","date":"2024-03-05","arxiv_id":"2403.03203","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-generalization-in-medical-visual","title":"Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation","date":"2024-03-05","arxiv_id":"2403.02707","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-collaborator-enabling-subjective","title":"Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use","date":"2024-03-05","arxiv_id":"2403.02626","repositories_listed":0,"syntology":null},{"url":null,"slug":"moka-open-vocabulary-robotic-manipulation","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","date":"2024-03-05","arxiv_id":"2403.03174","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-adaptable-and-attributable-language","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","date":"2024-03-05","arxiv_id":"2403.03187","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-traditional-chinese-evaluation","title":"An Improved Traditional Chinese Evaluation Suite for Foundation Model","date":"2024-03-04","arxiv_id":"2403.01858","repositories_listed":0,"syntology":null},{"url":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"answerability-in-retrieval-augmented-open","title":"Answerability in Retrieval-Augmented Open-Domain Question Answering","date":"2024-03-03","arxiv_id":"2403.01461","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-question-answer-generation-for-long","title":"Automatic Question-Answer Generation for Long-Tail Knowledge","date":"2024-03-03","arxiv_id":"2403.01382","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-lingual-representation-for","title":"Improving Cross-lingual Representation for Semantic Retrieval with Code-switching","date":"2024-03-03","arxiv_id":"2403.01364","repositories_listed":0,"syntology":null},{"url":null,"slug":"kormedmcqa-multi-choice-question-answering","title":"KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations","date":"2024-03-03","arxiv_id":"2403.01469","repositories_listed":0,"syntology":null},{"url":null,"slug":"right-for-right-reasons-large-language-models","title":"Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering","date":"2024-03-03","arxiv_id":"2403.01390","repositories_listed":0,"syntology":null},{"url":null,"slug":"api-is-enough-conformal-prediction-for-large","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","date":"2024-03-02","arxiv_id":"2403.01216","repositories_listed":0,"syntology":null},{"url":null,"slug":"vbart-the-turkish-llm","title":"VBART: The Turkish LLM","date":"2024-03-02","arxiv_id":"2403.01308","repositories_listed":0,"syntology":null},{"url":"/paper/mediswift-efficient-sparse-pre-trained","slug":"mediswift-efficient-sparse-pre-trained","title":"MediSwift: Efficient Sparse Pre-trained Biomedical Language Models","date":"2024-03-01","arxiv_id":"2403.00952","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-arxiv-a-dataset-for-improving","title":"Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models","date":"2024-03-01","arxiv_id":"2403.00231","repositories_listed":0,"syntology":null},{"url":null,"slug":"openmedlm-prompt-engineering-can-out-perform","title":"OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models","date":"2024-02-29","arxiv_id":"2402.19371","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-explicit-and-implicit-knowledge-for","title":"Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process","date":"2024-02-29","arxiv_id":"2402.19350","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-in-characterization-of-semantic-change","title":"Survey in Characterization of Semantic Change","date":"2024-02-29","arxiv_id":"2402.19088","repositories_listed":0,"syntology":null}],"record_sha256":"42378238f173d821bda1ea27848ed6b7e7e5c91ea0a12c97c69b34cf6c183f46","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}