{"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":"/method/gpt-4/papers/4","list_of":"/method/gpt-4","method":"GPT-4","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":4,"pages_in_order":29,"rows_per_page":100,"rows":[301,400],"of":2870,"counts":{"archive_papers_tagged":2870,"with_a_code_link":1244,"where_syntology_ran_a_sample":526,"not_listed_spam_title":0,"listed":2870,"listed_where_code_ran":526,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":417,"every_run_a_failure_of_syntologys_instrument":109,"listed_with_a_run_with_no_instrument_failure":417,"listed_every_run_a_failure_of_syntologys_instrument":109,"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":"/method/gpt-4","prev":"/method/gpt-4/papers/3","next":"/method/gpt-4/papers/5","papers":[{"paper":null,"slug":"decentralized-low-rank-fine-tuning-of-large","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","date":"2025-01-26","arxiv_id":"2501.15361","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-estonian-text-simplification","title":"Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets","date":"2025-01-26","arxiv_id":"2501.15624","n_code_links":0,"syntology":null},{"paper":"/paper/sedareval-automated-evaluation-using-self","slug":"sedareval-automated-evaluation-using-self","title":"SedarEval: Automated Evaluation using Self-Adaptive Rubrics","date":"2025-01-26","arxiv_id":"2501.15595","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wwn1233/sedareval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-ai-driven-live-systematic-reviews-in-the","slug":"an-ai-driven-live-systematic-reviews-in-the","title":"An AI-Driven Live Systematic Reviews in the Brain-Heart Interconnectome: Minimizing Research Waste and Advancing Evidence Synthesis","date":"2025-01-25","arxiv_id":"2501.17181","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-hierarchy-guided-biological-medical","title":"Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training","date":"2025-01-25","arxiv_id":"2501.15108","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-evaluation-based-on-aerospace","title":"LLM Evaluation Based on Aerospace Manufacturing Expertise: Automated Generation and Multi-Model Question Answering","date":"2025-01-25","arxiv_id":"2501.17183","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-education","title":"Using Large Language Models for education managements in Vietnamese with low resources","date":"2025-01-25","arxiv_id":"2501.15022","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-table-instruction-tuning","slug":"rethinking-table-instruction-tuning","title":"Rethinking Table Instruction Tuning","date":"2025-01-24","arxiv_id":"2501.14693","n_code_links":1,"syntology":null},{"paper":null,"slug":"test-time-code-switching-for-cross-lingual","title":"Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction","date":"2025-01-24","arxiv_id":"2501.14144","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-biomedical-relation-extraction-with-1","slug":"enhancing-biomedical-relation-extraction-with-1","title":"Enhancing Biomedical Relation Extraction with Directionality","date":"2025-01-23","arxiv_id":"2501.14079","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-are-vulnerable-to-malicious-prompts","title":"LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language","date":"2025-01-23","arxiv_id":"2501.14073","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-can-plan-only-if-we-tell-them","title":"LLMs Can Plan Only If We Tell Them","date":"2025-01-23","arxiv_id":"2501.13545","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-answering-on-patient-medical-records","title":"Question Answering on Patient Medical Records with Private Fine-Tuned LLMs","date":"2025-01-23","arxiv_id":"2501.13687","n_code_links":0,"syntology":null},{"paper":null,"slug":"sigma-differential-rescaling-of-query-key-and","title":"Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models","date":"2025-01-23","arxiv_id":"2501.13629","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-labelling-with-open-source-llms","title":"Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration","date":"2025-01-21","arxiv_id":"2501.12332","n_code_links":0,"syntology":null},{"paper":"/paper/episodic-memories-generation-and-evaluation","slug":"episodic-memories-generation-and-evaluation","title":"Episodic Memories Generation and Evaluation Benchmark for Large Language Models","date":"2025-01-21","arxiv_id":"2501.13121","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":13,"n_instrument":0,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ahstat/episodic-memory-benchmark"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"keir-ecir-2025-the-second-workshop-on","title":"KEIR @ ECIR 2025: The Second Workshop on Knowledge-Enhanced Information Retrieval","date":"2025-01-20","arxiv_id":"2501.11499","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-reasoning-towards-unified","title":"Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective","date":"2025-01-19","arxiv_id":"2501.11110","n_code_links":0,"syntology":null},{"paper":"/paper/pasa-an-llm-agent-for-comprehensive-academic","slug":"pasa-an-llm-agent-for-comprehensive-academic","title":"PaSa: An LLM Agent for Comprehensive Academic Paper Search","date":"2025-01-17","arxiv_id":"2501.10120","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bytedance/pasa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"perspective-transition-of-large-language","title":"Perspective Transition of Large Language Models for Solving Subjective Tasks","date":"2025-01-16","arxiv_id":"2501.09265","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-large-language-models-for-effective","title":"Enhanced Large Language Models for Effective Screening of Depression and Anxiety","date":"2025-01-15","arxiv_id":"2501.08769","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-narrative-clustering-in-large","title":"Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT","date":"2025-01-14","arxiv_id":"2501.08053","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-text-classification","title":"Large Language Models For Text Classification: Case Study And Comprehensive Review","date":"2025-01-14","arxiv_id":"2501.08457","n_code_links":0,"syntology":null},{"paper":"/paper/pokerbench-training-large-language-models-to","slug":"pokerbench-training-large-language-models-to","title":"PokerBench: Training Large Language Models to become Professional Poker Players","date":"2025-01-14","arxiv_id":"2501.08328","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-artificial-intelligence-supported","title":"Generative Artificial Intelligence-Supported Pentesting: A Comparison between Claude Opus, GPT-4, and Copilot","date":"2025-01-12","arxiv_id":"2501.06963","n_code_links":0,"syntology":null},{"paper":"/paper/zno-eval-benchmarking-reasoning-capabilities","slug":"zno-eval-benchmarking-reasoning-capabilities","title":"ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian","date":"2025-01-12","arxiv_id":"2501.06715","n_code_links":1,"syntology":null},{"paper":null,"slug":"iconicity-in-large-language-models","title":"Iconicity in Large Language Models","date":"2025-01-10","arxiv_id":"2501.05643","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-inversion-in-split-learning-for","title":"Model Inversion in Split Learning for Personalized LLMs: New Insights from Information Bottleneck Theory","date":"2025-01-10","arxiv_id":"2501.05965","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-streamline-automated","title":"Large language models streamline automated systematic review: A preliminary study","date":"2025-01-09","arxiv_id":"2502.15702","n_code_links":0,"syntology":null},{"paper":null,"slug":"longvitu-instruction-tuning-for-long-form","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","date":"2025-01-09","arxiv_id":"2501.05037","n_code_links":0,"syntology":null},{"paper":null,"slug":"openai-chatgpt-interprets-radiological-images","title":"OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up","date":"2025-01-09","arxiv_id":"2501.06269","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-dynamics-of-meaning-through-time","title":"The dynamics of meaning through time: Assessment of Large Language Models","date":"2025-01-09","arxiv_id":"2501.05552","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-and-planning-in-robotic-navigation-a","title":"Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models","date":"2025-01-07","arxiv_id":"2501.05478","n_code_links":0,"syntology":null},{"paper":null,"slug":"developing-an-artificial-intelligence-tool","title":"Developing an Artificial Intelligence Tool for Personalized Breast Cancer Treatment Plans based on the NCCN Guidelines","date":"2025-01-06","arxiv_id":"2502.15698","n_code_links":0,"syntology":null},{"paper":null,"slug":"vicsim-enhancing-victim-simulation-with","title":"VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity","date":"2025-01-06","arxiv_id":"2501.03139","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-against","title":"Evaluating Large Language Models Against Human Annotators in Latent Content Analysis: Sentiment, Political Leaning, Emotional Intensity, and Sarcasm","date":"2025-01-05","arxiv_id":"2501.02532","n_code_links":0,"syntology":null},{"paper":null,"slug":"honkaichat-companions-from-anime-that-feel","title":"HonkaiChat: Companions from Anime that feel alive!","date":"2025-01-05","arxiv_id":"2501.03277","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-new-benchmark-for-ai-alignment","title":"Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI","date":"2025-01-05","arxiv_id":"2501.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-robustness-of-homogeneity-bias","title":"Examining the Robustness of Homogeneity Bias to Hyperparameter Adjustments in GPT-4","date":"2025-01-04","arxiv_id":"2501.02211","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-capabilities-and-limitations-of-1","title":"Exploring the Capabilities and Limitations of Large Language Models for Radiation Oncology Decision Support","date":"2025-01-04","arxiv_id":"2501.02346","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-application-of-large-language-models-in","title":"The Application of Large Language Models in Recommendation Systems","date":"2025-01-04","arxiv_id":"2501.02178","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifier-guided-captioning-across","title":"Classifier-Guided Captioning Across Modalities","date":"2025-01-03","arxiv_id":"2501.03183","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-legal-aid-understanding-legal-needs","title":"LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries","date":"2025-01-03","arxiv_id":"2501.01711","n_code_links":0,"syntology":null},{"paper":"/paper/mirage-exploring-how-large-language-models","slug":"mirage-exploring-how-large-language-models","title":"MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments","date":"2025-01-03","arxiv_id":"2501.01652","n_code_links":1,"syntology":null},{"paper":"/paper/turning-logic-against-itself-probing-model","slug":"turning-logic-against-itself-probing-model","title":"Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions","date":"2025-01-03","arxiv_id":"2501.01872","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ukplab/poate-attack"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"toward-inclusive-educational-ai-auditing","title":"Toward Inclusive Educational AI: Auditing Frontier LLMs through a Multiplexity Lens","date":"2025-01-02","arxiv_id":"2501.03259","n_code_links":0,"syntology":null},{"paper":"/paper/column-property-annotation-using-large","slug":"column-property-annotation-using-large","title":"Column Property Annotation using Large Language Models","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"r2c-mapping-room-to-chessboard-to-unlock-llm","title":"R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"separation-of-powers-on-segregating-knowledge","title":"Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"yo-chameleon-personalized-vision-and-language","title":"Yo'Chameleon: Personalized Vision and Language Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"echoes-in-ai-quantifying-lack-of-plot","title":"Echoes in AI: Quantifying Lack of Plot Diversity in LLM Outputs","date":"2024-12-31","arxiv_id":"2501.00273","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-on-clinic-depression-assessment-an-llm","title":"GPT-4 on Clinic Depression Assessment: An LLM-Based Pilot Study","date":"2024-12-31","arxiv_id":"2501.00199","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-visual-language-priors-in-vlms","title":"Probing Visual Language Priors in VLMs","date":"2024-12-31","arxiv_id":"2501.00569","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-unsupervised-anomaly-detection-in","title":"An Unsupervised Anomaly Detection in Electricity Consumption Using Reinforcement Learning and Time Series Forest Based Framework","date":"2024-12-30","arxiv_id":"2501.00107","n_code_links":0,"syntology":null},{"paper":null,"slug":"casesumm-a-large-scale-dataset-for-long","title":"CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions","date":"2024-12-30","arxiv_id":"2501.00097","n_code_links":0,"syntology":null},{"paper":"/paper/facilitating-large-language-model-russian","slug":"facilitating-large-language-model-russian","title":"Facilitating large language model Russian adaptation with Learned Embedding Propagation","date":"2024-12-30","arxiv_id":"2412.21140","n_code_links":1,"syntology":null},{"paper":null,"slug":"nlp-based-regulatory-compliance-using-gpt-4-0","title":"NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents","date":"2024-12-29","arxiv_id":"2412.20602","n_code_links":0,"syntology":null},{"paper":null,"slug":"ddd-gendt-dynamic-data-driven-generative","title":"DDD-GenDT: Dynamic Data-driven Generative Digital Twin Framework","date":"2024-12-28","arxiv_id":"2501.00051","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-multi-agent-collaboration-with-tool","title":"Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering","date":"2024-12-28","arxiv_id":"2412.20145","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-alignment-based-knowledge","title":"Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models","date":"2024-12-27","arxiv_id":"2412.19449","n_code_links":0,"syntology":null},{"paper":"/paper/toward-adaptive-reasoning-in-large-language-1","slug":"toward-adaptive-reasoning-in-large-language-1","title":"Toward Adaptive Reasoning in Large Language Models with Thought Rollback","date":"2024-12-27","arxiv_id":"2412.19707","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["iQua/llmpebase"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/medec-a-benchmark-for-medical-error-detection","slug":"medec-a-benchmark-for-medical-error-detection","title":"MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes","date":"2024-12-26","arxiv_id":"2412.19260","n_code_links":1,"syntology":null},{"paper":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-large-language-models-with-an","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","date":"2024-12-25","arxiv_id":"2412.18729","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-automated","title":"Using Large Language Models for Automated Grading of Student Writing about Science","date":"2024-12-25","arxiv_id":"2412.18719","n_code_links":0,"syntology":null},{"paper":"/paper/decentralized-intelligence-in-gamefi-embodied","slug":"decentralized-intelligence-in-gamefi-embodied","title":"Decentralized Intelligence in GameFi: Embodied AI Agents and the Convergence of DeFi and Virtual Ecosystems","date":"2024-12-24","arxiv_id":"2412.18601","n_code_links":1,"syntology":null},{"paper":null,"slug":"evopat-a-multi-llm-based-patents","title":"EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent","date":"2024-12-24","arxiv_id":"2412.18100","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-mathematical-reasoning-advancing","slug":"multilingual-mathematical-reasoning-advancing","title":"Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and English","date":"2024-12-24","arxiv_id":"2412.18415","n_code_links":1,"syntology":null},{"paper":null,"slug":"timelyllm-segmented-llm-serving-system-for","title":"TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications","date":"2024-12-24","arxiv_id":"2412.18695","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-preference-data-synthetic","slug":"multimodal-preference-data-synthetic","title":"Multimodal Preference Data Synthetic Alignment with Reward Model","date":"2024-12-23","arxiv_id":"2412.17417","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-fusing-chatgpt-and-ensemble-learning-in","title":"On Fusing ChatGPT and Ensemble Learning in Discon-tinuous Named Entity Recognition in Health Corpora","date":"2024-12-22","arxiv_id":"2412.16976","n_code_links":0,"syntology":null},{"paper":null,"slug":"substationai-multimodal-large-model-based","title":"SubstationAI: Multimodal Large Model-Based Approaches for Analyzing Substation Equipment Faults","date":"2024-12-22","arxiv_id":"2412.17077","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptable-and-precise-enterprise-scenario-llm","title":"Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline","date":"2024-12-20","arxiv_id":"2412.15660","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-llms-and-slms-for-patient","title":"Benchmarking LLMs and SLMs for patient reported outcomes","date":"2024-12-20","arxiv_id":"2412.16291","n_code_links":0,"syntology":null},{"paper":null,"slug":"demystifying-the-potential-of-chatgpt-4","title":"Demystifying the Potential of ChatGPT-4 Vision for Construction Progress Monitoring","date":"2024-12-20","arxiv_id":"2412.16108","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanlike-cognitive-patterns-as-emergent","title":"Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models","date":"2024-12-20","arxiv_id":"2412.15501","n_code_links":0,"syntology":null},{"paper":"/paper/linguistic-features-extracted-by-gpt-4","slug":"linguistic-features-extracted-by-gpt-4","title":"Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech","date":"2024-12-20","arxiv_id":"2412.15772","n_code_links":1,"syntology":null},{"paper":null,"slug":"promptoptme-error-aware-prompt-compression","title":"PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics","date":"2024-12-20","arxiv_id":"2412.16120","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-good-is-gpt-at-writing-political-speeches","title":"How good is GPT at writing political speeches for the White House?","date":"2024-12-19","arxiv_id":"2412.14617","n_code_links":0,"syntology":null},{"paper":null,"slug":"systematic-evaluation-of-long-context-llms-on","title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","date":"2024-12-19","arxiv_id":"2412.15386","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-comparative-evaluation-of","slug":"fake-news-detection-comparative-evaluation-of","title":"Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data","date":"2024-12-18","arxiv_id":"2412.14276","n_code_links":1,"syntology":null},{"paper":"/paper/psydt-using-llms-to-construct-the-digital","slug":"psydt-using-llms-to-construct-the-digital","title":"PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling","date":"2024-12-18","arxiv_id":"2412.13660","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-from-automatic-1","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","date":"2024-12-18","arxiv_id":"2412.14308","n_code_links":0,"syntology":null},{"paper":"/paper/judgeblender-ensembling-judgments-for","slug":"judgeblender-ensembling-judgments-for","title":"JudgeBlender: Ensembling Judgments for Automatic Relevance Assessment","date":"2024-12-17","arxiv_id":"2412.13268","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-language-models-rival-mathematics","title":"Can Language Models Rival Mathematics Students? Evaluating Mathematical Reasoning through Textual Manipulation and Human Experiments","date":"2024-12-16","arxiv_id":"2412.11908","n_code_links":0,"syntology":null},{"paper":null,"slug":"openreviewer-a-specialized-large-language","title":"OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews","date":"2024-12-16","arxiv_id":"2412.11948","n_code_links":0,"syntology":null},{"paper":null,"slug":"second-language-arabic-acquisition-of-llms","title":"Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion","date":"2024-12-16","arxiv_id":"2412.12310","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-ai-assistance-on-radiology","title":"The Impact of AI Assistance on Radiology Reporting: A Pilot Study Using Simulated AI Draft Reports","date":"2024-12-16","arxiv_id":"2412.12042","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-open-source-advantage-in-large-language","title":"The Open Source Advantage in Large Language Models (LLMs)","date":"2024-12-16","arxiv_id":"2412.12004","n_code_links":0,"syntology":null},{"paper":"/paper/smaller-language-models-are-better","slug":"smaller-language-models-are-better","title":"Smaller Language Models Are Better Instruction Evolvers","date":"2024-12-15","arxiv_id":"2412.11231","n_code_links":1,"syntology":null},{"paper":"/paper/medg-krp-medical-graph-knowledge","slug":"medg-krp-medical-graph-knowledge","title":"MedG-KRP: Medical Graph Knowledge Representation Probing","date":"2024-12-14","arxiv_id":"2412.10982","n_code_links":1,"syntology":null},{"paper":"/paper/susgen-gpt-a-data-centric-llm-for-financial","slug":"susgen-gpt-a-data-centric-llm-for-financial","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","date":"2024-12-14","arxiv_id":"2412.10906","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-if-exploring-branching-narratives-by","title":"WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models","date":"2024-12-13","arxiv_id":"2412.10582","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-vulnerabilities-in-large-language","slug":"adversarial-vulnerabilities-in-large-language","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","date":"2024-12-11","arxiv_id":"2412.08099","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-personalized-ai-mentoring-with","title":"Assessing Personalized AI Mentoring with Large Language Models in the Computing Field","date":"2024-12-11","arxiv_id":"2412.08430","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-item-generation-for-personality","title":"Automatic Item Generation for Personality Situational Judgment Tests with Large Language Models","date":"2024-12-10","arxiv_id":"2412.12144","n_code_links":0,"syntology":null},{"paper":"/paper/bimedix2-bio-medical-expert-lmm-for-diverse","slug":"bimedix2-bio-medical-expert-lmm-for-diverse","title":"BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities","date":"2024-12-10","arxiv_id":"2412.07769","n_code_links":1,"syntology":null},{"paper":"/paper/conceptsearch-towards-efficient-program","slug":"conceptsearch-towards-efficient-program","title":"ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)","date":"2024-12-10","arxiv_id":"2412.07322","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-knowledge-graphs-from-large","title":"Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT","date":"2024-12-10","arxiv_id":"2412.07412","n_code_links":0,"syntology":null},{"paper":null,"slug":"ontology-driven-prompt-tuning-for-llm-based","title":"Ontology-driven Prompt Tuning for LLM-based Task and Motion Planning","date":"2024-12-10","arxiv_id":"2412.07493","n_code_links":0,"syntology":null}],"record_sha256":"dfbb65d0bf5f3b89984afd197f70f82a639a951f30cd6eb4f063f64025128dfd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}