{"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/59","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":59,"pages_in_order":109,"rows_per_page":100,"rows":[5801,5900],"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/58","next":"/task/question-answering/papers/60","papers":[{"url":null,"slug":"agent-hospital-a-simulacrum-of-hospital-with","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","date":"2024-05-05","arxiv_id":"2405.02957","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-rag-end-to-end-retrieval-augmented","title":"Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization","date":"2024-05-05","arxiv_id":"2405.02816","repositories_listed":0,"syntology":null},{"url":null,"slug":"r4-reinforced-retriever-reorder-responder-for","title":"R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models","date":"2024-05-04","arxiv_id":"2405.02659","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-retrieval-systems-in","title":"Comparative Analysis of Retrieval Systems in the Real World","date":"2024-05-03","arxiv_id":"2405.02048","repositories_listed":0,"syntology":null},{"url":null,"slug":"sukhsandesh-an-avatar-therapeutic-question","title":"SUKHSANDESH: An Avatar Therapeutic Question Answering Platform for Sexual Education in Rural India","date":"2024-05-03","arxiv_id":"2405.01858","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-human-vision-the-role-of-large-vision","title":"Beyond Human Vision: The Role of Large Vision Language Models in Microscope Image Analysis","date":"2024-05-01","arxiv_id":"2405.00876","repositories_listed":0,"syntology":null},{"url":null,"slug":"courseassist-pedagogically-appropriate","title":"CourseAssist: Pedagogically Appropriate AI Tutor for Computer Science Education","date":"2024-05-01","arxiv_id":"2407.10246","repositories_listed":0,"syntology":null},{"url":null,"slug":"crepe-coordinate-aware-end-to-end-document","title":"CREPE: Coordinate-Aware End-to-End Document Parser","date":"2024-05-01","arxiv_id":"2405.00260","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-visual-question-answering-a","title":"Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approach","date":"2024-05-01","arxiv_id":"2405.00479","repositories_listed":0,"syntology":null},{"url":null,"slug":"numllm-numeric-sensitive-large-language-model","title":"NumLLM: Numeric-Sensitive Large Language Model for Chinese Finance","date":"2024-05-01","arxiv_id":"2405.00566","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-hop-question-answering-over-knowledge","title":"Multi-hop Question Answering over Knowledge Graphs using Large Language Models","date":"2024-04-30","arxiv_id":"2404.19234","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-vision-to-language-image-reconstruction","title":"Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction","date":"2024-04-30","arxiv_id":"2404.19438","repositories_listed":0,"syntology":null},{"url":null,"slug":"qlsc-a-query-latent-semantic-calibrator-for","title":"QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering","date":"2024-04-30","arxiv_id":"2404.19316","repositories_listed":0,"syntology":null},{"url":null,"slug":"suvach-generated-hindi-qa-benchmark","title":"Suvach -- Generated Hindi QA benchmark","date":"2024-04-30","arxiv_id":"2404.19254","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-construction-of-theme-specific","title":"Automated Construction of Theme-specific Knowledge Graphs","date":"2024-04-29","arxiv_id":"2404.19146","repositories_listed":0,"syntology":null},{"url":"/paper/capabilities-of-gemini-models-in-medicine","slug":"capabilities-of-gemini-models-in-medicine","title":"Capabilities of Gemini Models in Medicine","date":"2024-04-29","arxiv_id":"2404.18416","repositories_listed":0,"syntology":null},{"url":null,"slug":"qana-llm-based-question-generation-and","title":"QANA: LLM-based Question Generation and Network Analysis for Zero-shot Key Point Analysis and Beyond","date":"2024-04-29","arxiv_id":"2404.18371","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-pre-training-for-cross-lingual-llm","title":"Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities","date":"2024-04-27","arxiv_id":"2404.17790","repositories_listed":0,"syntology":null},{"url":null,"slug":"tool-calling-enhancing-medication","title":"Tool Calling: Enhancing Medication Consultation via Retrieval-Augmented Large Language Models","date":"2024-04-27","arxiv_id":"2404.17897","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-enhanced-single-choice","title":"Transfer Learning Enhanced Single-choice Decision for Multi-choice Question Answering","date":"2024-04-27","arxiv_id":"2404.17949","repositories_listed":0,"syntology":null},{"url":null,"slug":"2m-ner-contrastive-learning-for-multilingual","title":"2M-NER: Contrastive Learning for Multilingual and Multimodal NER with Language and Modal Fusion","date":"2024-04-26","arxiv_id":"2404.17122","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-generation-with-knowledge","title":"Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering","date":"2024-04-26","arxiv_id":"2404.17723","repositories_listed":0,"syntology":null},{"url":null,"slug":"tigqa-an-expert-annotated-question-answering","title":"TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya","date":"2024-04-26","arxiv_id":"2404.17194","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiency-in-focus-layernorm-as-a-catalyst","title":"Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models","date":"2024-04-25","arxiv_id":"2404.16385","repositories_listed":0,"syntology":null},{"url":null,"slug":"turkce-dil-modellerinin-performans","title":"Türkçe Dil Modellerinin Performans Karşılaştırması Performance Comparison of Turkish Language Models","date":"2024-04-25","arxiv_id":"2404.17010","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-evaluating-large","title":"A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry","date":"2024-04-24","arxiv_id":"2404.15777","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-potential-of-mid-sized-language","title":"Assessing The Potential Of Mid-Sized Language Models For Clinical QA","date":"2024-04-24","arxiv_id":"2404.15894","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-vs-gpt-for-financial-engineering","title":"BERT vs GPT for financial engineering","date":"2024-04-24","arxiv_id":"2405.12990","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-of-domain-adapted-vision-and-language","title":"Fusion of Domain-Adapted Vision and Language Models for Medical Visual Question Answering","date":"2024-04-24","arxiv_id":"2404.16192","repositories_listed":0,"syntology":null},{"url":null,"slug":"ks-llm-knowledge-selection-of-large-language","title":"KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering","date":"2024-04-24","arxiv_id":"2404.15660","repositories_listed":0,"syntology":null},{"url":null,"slug":"porting-large-language-models-to-mobile","title":"Porting Large Language Models to Mobile Devices for Question Answering","date":"2024-04-24","arxiv_id":"2404.15851","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-tool-augmented-agents-in-remote","title":"Evaluating Tool-Augmented Agents in Remote Sensing Platforms","date":"2024-04-23","arxiv_id":"2405.00709","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-knowledge-enhanced-medical-vlp-for","title":"Grounded Knowledge-Enhanced Medical VLP for Chest X-Ray","date":"2024-04-23","arxiv_id":"2404.14750","repositories_listed":0,"syntology":null},{"url":null,"slug":"med42-evaluating-fine-tuning-strategies-for","title":"Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches","date":"2024-04-23","arxiv_id":"2404.14779","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-content-aware-indexing-for-long","title":"Multi-view Content-aware Indexing for Long Document Retrieval","date":"2024-04-23","arxiv_id":"2404.15103","repositories_listed":0,"syntology":null},{"url":null,"slug":"pegasus-v1-technical-report","title":"Pegasus-v1 Technical Report","date":"2024-04-23","arxiv_id":"2404.14687","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-generation-for-domain","title":"Retrieval Augmented Generation for Domain-specific Question Answering","date":"2024-04-23","arxiv_id":"2404.14760","repositories_listed":0,"syntology":null},{"url":null,"slug":"wiki-llava-hierarchical-retrieval-augmented","title":"Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs","date":"2024-04-23","arxiv_id":"2404.15406","repositories_listed":0,"syntology":null},{"url":null,"slug":"xc-cache-cross-attending-to-cached-context","title":"XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference","date":"2024-04-23","arxiv_id":"2404.15420","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-design-for-human-feedback","title":"Optimal Design for Human Preference Elicitation","date":"2024-04-22","arxiv_id":"2404.13895","repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-of-reviews-a-tree-based-dynamic","title":"Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering","date":"2024-04-22","arxiv_id":"2404.14464","repositories_listed":0,"syntology":null},{"url":null,"slug":"wanglab-at-mediqa-corr-2024-optimized-llm","title":"WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction","date":"2024-04-22","arxiv_id":"2404.14544","repositories_listed":0,"syntology":null},{"url":null,"slug":"wanglab-at-mediqa-m3g-2024-multimodal-medical","title":"WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models","date":"2024-04-22","arxiv_id":"2404.14567","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-diverse-methods-in-visual-question","title":"Exploring Diverse Methods in Visual Question Answering","date":"2024-04-21","arxiv_id":"2404.13565","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-question-quality-on-stackoverflow","title":"Predicting Question Quality on StackOverflow with Neural Networks","date":"2024-04-20","arxiv_id":"2404.14449","repositories_listed":0,"syntology":null},{"url":null,"slug":"eyes-can-deceive-benchmarking-counterfactual","title":"Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning","date":"2024-04-19","arxiv_id":"2404.12966","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-phyrlhf-reinforcement-learning-framework","title":"MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering","date":"2024-04-19","arxiv_id":"2404.12926","repositories_listed":0,"syntology":null},{"url":null,"slug":"pdf-mvqa-a-dataset-for-multimodal-information","title":"PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering","date":"2024-04-19","arxiv_id":"2404.12720","repositories_listed":0,"syntology":null},{"url":null,"slug":"textsquare-scaling-up-text-centric-visual","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","date":"2024-04-19","arxiv_id":"2404.12803","repositories_listed":0,"syntology":null},{"url":null,"slug":"emrqa-msquad-a-medical-dataset-structured","title":"emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information","date":"2024-04-18","arxiv_id":"2404.12050","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-length-extrapolation-in-sequential","title":"Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory","date":"2024-04-18","arxiv_id":"2404.11870","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-ai-for-law-bridging-the-gap-with","title":"Evaluating AI for Law: Bridging the Gap with Open-Source Solutions","date":"2024-04-18","arxiv_id":"2404.12349","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucibot-is-there-no-such-thing-as-a-bad","title":"Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing","date":"2024-04-18","arxiv_id":"2404.12535","repositories_listed":0,"syntology":null},{"url":null,"slug":"medthink-explaining-medical-visual-question","title":"MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale","date":"2024-04-18","arxiv_id":"2404.12372","repositories_listed":0,"syntology":null},{"url":null,"slug":"reka-core-flash-and-edge-a-series-of-powerful","title":"Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models","date":"2024-04-18","arxiv_id":"2404.12387","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-q-a-with-domain-specific-fine","title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","date":"2024-04-17","arxiv_id":"2404.11792","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-span-extraction-in-generative","title":"Evaluating Span Extraction in Generative Paradigm: A Reflection on Aspect-Based Sentiment Analysis","date":"2024-04-17","arxiv_id":"2404.11539","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-still-struggle-to-zero-shot","title":"Language Models Still Struggle to Zero-shot Reason about Time Series","date":"2024-04-17","arxiv_id":"2404.11757","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-controlled-motion-mamba-text-instructed","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","date":"2024-04-17","arxiv_id":"2404.11375","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistency-and-uncertainty-identifying","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","date":"2024-04-16","arxiv_id":"2404.10193","repositories_listed":0,"syntology":null},{"url":null,"slug":"cotar-chain-of-thought-attribution-reasoning","title":"CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity","date":"2024-04-16","arxiv_id":"2404.10513","repositories_listed":0,"syntology":null},{"url":null,"slug":"find-the-gap-knowledge-base-reasoning-for","title":"Find The Gap: Knowledge Base Reasoning For Visual Question Answering","date":"2024-04-16","arxiv_id":"2404.10226","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-on-efficient-knowledge-paths","title":"Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering","date":"2024-04-16","arxiv_id":"2404.10384","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-based-abstention-in-llms-improves","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","date":"2024-04-16","arxiv_id":"2404.10960","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-ref-hand-object-interaction-referral-in","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","date":"2024-04-15","arxiv_id":"2404.09933","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-table-retrieval-a-solved-problem-join","title":"Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval","date":"2024-04-15","arxiv_id":"2404.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-data-knowledge-graph-construction-for","title":"Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT","date":"2024-04-14","arxiv_id":"2404.09296","repositories_listed":0,"syntology":null},{"url":null,"slug":"gemquad-generating-multilingual-question","title":"GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning","date":"2024-04-14","arxiv_id":"2404.09163","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-llm-evaluation-focused-on-metrics","title":"Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions","date":"2024-04-14","arxiv_id":"2404.09135","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-and-updating-language-and-domain","title":"Pretraining and Updates of Domain-Specific LLM: A Case Study in the Japanese Business Domain","date":"2024-04-12","arxiv_id":"2404.08262","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-dialogues-dialogues-dataset-for-audio","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","date":"2024-04-11","arxiv_id":"2404.07616","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-phyqa-multimodal-physics-question","title":"MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting","date":"2024-04-11","arxiv_id":"2404.08704","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-unified-prompt-tuning-for-request-quality","title":"On Unified Prompt Tuning for Request Quality Assurance in Public Code Review","date":"2024-04-11","arxiv_id":"2404.07942","repositories_listed":0,"syntology":null},{"url":null,"slug":"risklabs-predicting-financial-risk-using","title":"RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data","date":"2024-04-11","arxiv_id":"2404.07452","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-the-dilemma-of-ai-errors-exploring","title":"Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models","date":"2024-04-11","arxiv_id":"2404.07725","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-question-answering-for-enterprise","title":"Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Models","date":"2024-04-10","arxiv_id":"2404.08695","repositories_listed":0,"syntology":null},{"url":null,"slug":"groundedness-in-retrieval-augmented-long-form","title":"Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study","date":"2024-04-10","arxiv_id":"2404.07060","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-shopping-intent-in-product-qa-for","title":"Identifying Shopping Intent in Product QA for Proactive Recommendations","date":"2024-04-09","arxiv_id":"2404.06017","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-reading-comprehension-is-affected-by","title":"LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements","date":"2024-04-09","arxiv_id":"2404.06283","repositories_listed":0,"syntology":null},{"url":"/paper/morevqa-exploring-modular-reasoning-models","slug":"morevqa-exploring-modular-reasoning-models","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","date":"2024-04-09","arxiv_id":"2404.06511","repositories_listed":0,"syntology":null},{"url":null,"slug":"surveyagent-a-conversational-system-for","title":"SurveyAgent: A Conversational System for Personalized and Efficient Research Survey","date":"2024-04-09","arxiv_id":"2404.06364","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-study-on-german-language-models","title":"Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding","date":"2024-04-08","arxiv_id":"2404.05694","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-software-related-information","title":"Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language Models","date":"2024-04-08","arxiv_id":"2404.05587","repositories_listed":0,"syntology":null},{"url":null,"slug":"hammr-hierarchical-multimodal-react-agents","title":"HAMMR: HierArchical MultiModal React agents for generic VQA","date":"2024-04-08","arxiv_id":"2404.05465","repositories_listed":0,"syntology":null},{"url":null,"slug":"medexpqa-multilingual-benchmarking-of-large","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","date":"2024-04-08","arxiv_id":"2404.05590","repositories_listed":0,"syntology":null},{"url":null,"slug":"perkwe-coqa-enhance-persian-conversational","title":"PerkwE_COQA: Enhanced Persian Conversational Question Answering by combining contextual keyword extraction with Large Language Models","date":"2024-04-08","arxiv_id":"2404.05406","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-stealth-adversarial-text-attacks-on","title":"Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods","date":"2024-04-08","arxiv_id":"2404.05159","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hallucinations-leaderboard-an-open-effort","title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","date":"2024-04-08","arxiv_id":"2404.05904","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-eda-synthesis-errors-with-llms","title":"LLM-aided explanations of EDA synthesis errors","date":"2024-04-07","arxiv_id":"2404.07235","repositories_listed":0,"syntology":null},{"url":null,"slug":"fractal-fine-grained-scoring-from-aggregate","title":"FRACTAL: Fine-Grained Scoring from Aggregate Text Labels","date":"2024-04-07","arxiv_id":"2404.04817","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-vars-introducing-explainability-in-football","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model","date":"2024-04-07","arxiv_id":"2404.06332","repositories_listed":0,"syntology":null},{"url":null,"slug":"your-finetuned-large-language-model-is","title":"Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector","date":"2024-04-07","arxiv_id":"2404.08679","repositories_listed":0,"syntology":null},{"url":null,"slug":"multicalibration-for-confidence-scoring-in","title":"Multicalibration for Confidence Scoring in LLMs","date":"2024-04-06","arxiv_id":"2404.04689","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-large-language-models-for","title":"Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement","date":"2024-04-06","arxiv_id":"2404.04627","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-response-shaping","title":"Best Response Shaping","date":"2024-04-05","arxiv_id":"2404.06519","repositories_listed":0,"syntology":null},{"url":null,"slug":"buddie-a-business-document-dataset-for-multi","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","date":"2024-04-05","arxiv_id":"2404.04003","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-sentence-transformers-learn-quasi","title":"Do Sentence Transformers Learn Quasi-Geospatial Concepts from General Text?","date":"2024-04-05","arxiv_id":"2404.04169","repositories_listed":0,"syntology":null},{"url":null,"slug":"koala-key-frame-conditioned-long-video-llm","title":"Koala: Key frame-conditioned long video-LLM","date":"2024-04-05","arxiv_id":"2404.04346","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-symbolic-videoqa-learning","title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering","date":"2024-04-05","arxiv_id":"2404.04007","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-small-language-models-help-large-language","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","date":"2024-04-04","arxiv_id":"2404.03414","repositories_listed":0,"syntology":null}],"record_sha256":"bc8629c98bd6a69d022add189d2cad98b80c063b006381a6e2c00e2ad9c4b139","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}