{"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/8","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":8,"pages_in_order":29,"rows_per_page":100,"rows":[701,800],"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/7","next":"/method/gpt-4/papers/9","papers":[{"paper":null,"slug":"detection-made-easy-potentials-of-large","title":"Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities","date":"2024-09-15","arxiv_id":"2409.10574","n_code_links":0,"syntology":null},{"paper":null,"slug":"gp-gpt-large-language-model-for-gene","title":"GP-GPT: Large Language Model for Gene-Phenotype Mapping","date":"2024-09-15","arxiv_id":"2409.09825","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-open-source-large-language-models-1","title":"Leveraging Open-Source Large Language Models for Native Language Identification","date":"2024-09-15","arxiv_id":"2409.09659","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-gender-bias-in-large-language","slug":"unveiling-gender-bias-in-large-language","title":"Unveiling Gender Bias in Large Language Models: Using Teacher's Evaluation in Higher Education As an Example","date":"2024-09-15","arxiv_id":"2409.09652","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-evaluation-of-using-chatgpt-to","title":"An empirical evaluation of using ChatGPT to summarize disputes for recommending similar labor and employment cases in Chinese","date":"2024-09-14","arxiv_id":"2409.09280","n_code_links":0,"syntology":null},{"paper":null,"slug":"keeping-humans-in-the-loop-human-centered","title":"Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI","date":"2024-09-14","arxiv_id":"2409.09467","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-rag-approach-for-generating-competency","title":"A RAG Approach for Generating Competency Questions in Ontology Engineering","date":"2024-09-13","arxiv_id":"2409.08820","n_code_links":0,"syntology":null},{"paper":"/paper/changechat-an-interactive-model-for-remote","slug":"changechat-an-interactive-model-for-remote","title":"ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning","date":"2024-09-13","arxiv_id":"2409.08582","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hanlinwu/changechat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"kodexv0-1-a-family-of-state-of-the-art","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","date":"2024-09-13","arxiv_id":"2409.13749","n_code_links":0,"syntology":null},{"paper":null,"slug":"online-vs-offline-a-comparative-study-of","title":"Online vs Offline: A Comparative Study of First-Party and Third-Party Evaluations of Social Chatbots","date":"2024-09-12","arxiv_id":"2409.07823","n_code_links":0,"syntology":null},{"paper":"/paper/a-fine-grained-sentiment-analysis-of-app","slug":"a-fine-grained-sentiment-analysis-of-app","title":"How Effectively Do LLMs Extract Feature-Sentiment Pairs from App Reviews?","date":"2024-09-11","arxiv_id":"2409.07162","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-we-count-on-llms-the-fixed-effect-fallacy","title":"Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilities","date":"2024-09-11","arxiv_id":"2409.07638","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-emotion-recognition-with-vision","title":"Multimodal Emotion Recognition with Vision-language Prompting and Modality Dropout","date":"2024-09-11","arxiv_id":"2409.07078","n_code_links":0,"syntology":null},{"paper":null,"slug":"simulbench-evaluating-language-models-with","title":"SimulBench: Evaluating Language Models with Creative Simulation Tasks","date":"2024-09-11","arxiv_id":"2409.07641","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-less-is-not-more-large-language-models","title":"Mapping Biomedical Ontology Terms to IDs: Effect of Domain Prevalence on Prediction Accuracy","date":"2024-09-11","arxiv_id":"2409.13746","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dataset-for-evaluating-llm-based-evaluation","title":"A Dataset for Evaluating LLM-based Evaluation Functions for Research Question Extraction Task","date":"2024-09-10","arxiv_id":"2409.06883","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-unlock-novel","slug":"can-large-language-models-unlock-novel","title":"Can Large Language Models Unlock Novel Scientific Research Ideas?","date":"2024-09-10","arxiv_id":"2409.06185","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":2,"n_instrument":0,"unverified":9,"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) · 9 unverified","official":{"repos":["sandeep82945/future-idea-generation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/grouse-a-benchmark-to-evaluate-evaluators-in","slug":"grouse-a-benchmark-to-evaluate-evaluators-in","title":"GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering","date":"2024-09-10","arxiv_id":"2409.06595","n_code_links":1,"syntology":null},{"paper":"/paper/what-is-the-role-of-small-models-in-the-llm","slug":"what-is-the-role-of-small-models-in-the-llm","title":"What is the Role of Small Models in the LLM Era: A Survey","date":"2024-09-10","arxiv_id":"2409.06857","n_code_links":1,"syntology":null},{"paper":"/paper/2409-13727","slug":"2409-13727","title":"Classification performance and reproducibility of GPT-4 omni for information extraction from veterinary electronic health records","date":"2024-09-09","arxiv_id":"2409.13727","n_code_links":1,"syntology":null},{"paper":null,"slug":"fairhome-a-fair-housing-and-fair-lending","title":"FairHome: A Fair Housing and Fair Lending Dataset","date":"2024-09-09","arxiv_id":"2409.05990","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-the-sources-of-ideological-bias","title":"Identifying the sources of ideological bias in GPT models through linguistic variation in output","date":"2024-09-09","arxiv_id":"2409.06043","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-building-a-robust-knowledge-intensive","title":"Towards Building a Robust Knowledge Intensive Question Answering Model with Large Language Models","date":"2024-09-09","arxiv_id":"2409.05385","n_code_links":0,"syntology":null},{"paper":null,"slug":"vidlpro-a-underline-vid-eo-underline-l","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","date":"2024-09-07","arxiv_id":"2409.04732","n_code_links":0,"syntology":null},{"paper":"/paper/anymatch-efficient-zero-shot-entity-matching","slug":"anymatch-efficient-zero-shot-entity-matching","title":"AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model","date":"2024-09-06","arxiv_id":"2409.04073","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-llms-and-knowledge-graphs-to-reduce","title":"Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Question Answering","date":"2024-09-06","arxiv_id":"2409.04181","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-based-incident","title":"Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support","date":"2024-09-06","arxiv_id":"2409.13707","n_code_links":0,"syntology":null},{"paper":null,"slug":"ui-jepa-towards-active-perception-of-user","title":"UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity","date":"2024-09-06","arxiv_id":"2409.04081","n_code_links":0,"syntology":null},{"paper":"/paper/cacer-clinical-concept-annotations-for-cancer","slug":"cacer-clinical-concept-annotations-for-cancer","title":"CACER: Clinical Concept Annotations for Cancer Events and Relations","date":"2024-09-05","arxiv_id":"2409.03905","n_code_links":1,"syntology":null},{"paper":null,"slug":"materialbench-evaluating-college-level","title":"MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models","date":"2024-09-05","arxiv_id":"2409.03161","n_code_links":0,"syntology":null},{"paper":"/paper/xlam-a-family-of-large-action-models-to","slug":"xlam-a-family-of-large-action-models-to","title":"xLAM: A Family of Large Action Models to Empower AI Agent Systems","date":"2024-09-05","arxiv_id":"2409.03215","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-calls-to-action-in-multimodal","title":"Detecting Calls to Action in Multimodal Content: Analysis of the 2021 German Federal Election Campaign on Instagram","date":"2024-09-04","arxiv_id":"2409.02690","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-privacy-savvy-are-large-language-models-a","title":"How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review","date":"2024-09-04","arxiv_id":"2409.02375","n_code_links":0,"syntology":null},{"paper":"/paper/hypothesizing-missing-causal-variables-with","slug":"hypothesizing-missing-causal-variables-with","title":"Hypothesizing Missing Causal Variables with LLMs","date":"2024-09-04","arxiv_id":"2409.02604","n_code_links":1,"syntology":null},{"paper":null,"slug":"irrelevant-alternatives-bias-large-language","title":"Irrelevant Alternatives Bias Large Language Model Hiring Decisions","date":"2024-09-04","arxiv_id":"2409.15299","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-solving","title":"Leveraging Large Language Models for Solving Rare MIP Challenges","date":"2024-09-03","arxiv_id":"2409.04464","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-instructed-derived-prompt-generation","title":"Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs","date":"2024-09-03","arxiv_id":"2409.01552","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-versus-classical","slug":"large-language-models-versus-classical","title":"Large Language Models versus Classical Machine Learning: Performance in COVID-19 Mortality Prediction Using High-Dimensional Tabular Data","date":"2024-09-02","arxiv_id":"2409.02136","n_code_links":2,"syntology":null},{"paper":"/paper/self-judge-selective-instruction-following","slug":"self-judge-selective-instruction-following","title":"Self-Judge: Selective Instruction Following with Alignment Self-Evaluation","date":"2024-09-02","arxiv_id":"2409.00935","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["nusnlp/Self-J"],"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":null,"slug":"toolace-winning-the-points-of-llm-function","title":"ToolACE: Winning the Points of LLM Function Calling","date":"2024-09-02","arxiv_id":"2409.00920","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-on-information-extraction","title":"An Empirical Study on Information Extraction using Large Language Models","date":"2024-08-31","arxiv_id":"2409.00369","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatting-up-attachment-using-llms-to-predict","title":"Chatting Up Attachment: Using LLMs to Predict Adult Bonds","date":"2024-08-31","arxiv_id":"2409.00347","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-large-language-3","title":"Evaluating the Performance of Large Language Models in Competitive Programming: A Multi-Year, Multi-Grade Analysis","date":"2024-08-31","arxiv_id":"2409.09054","n_code_links":0,"syntology":null},{"paper":"/paper/longrecipe-recipe-for-efficient-long-context","slug":"longrecipe-recipe-for-efficient-long-context","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","date":"2024-08-31","arxiv_id":"2409.00509","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhiyuanhubj/LongRecipe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-event-reasoning-in-large-language","title":"Enhancing Event Reasoning in Large Language Models through Instruction Fine-Tuning with Semantic Causal Graphs","date":"2024-08-30","arxiv_id":"2409.00209","n_code_links":0,"syntology":null},{"paper":"/paper/from-text-to-emotion-unveiling-the-emotion","slug":"from-text-to-emotion-unveiling-the-emotion","title":"From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs","date":"2024-08-30","arxiv_id":"2408.17026","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-a-cognitive-model-to-measure","title":"Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content","date":"2024-08-30","arxiv_id":"2409.00269","n_code_links":0,"syntology":null},{"paper":null,"slug":"orthodoc-multimodal-large-language-model-for","title":"OrthoDoc: Multimodal Large Language Model for Assisting Diagnosis in Computed Tomography","date":"2024-08-30","arxiv_id":"2409.09052","n_code_links":0,"syntology":null},{"paper":"/paper/progres-prompted-generative-rescoring-on-asr","slug":"progres-prompted-generative-rescoring-on-asr","title":"ProGRes: Prompted Generative Rescoring on ASR n-Best","date":"2024-08-30","arxiv_id":"2409.00217","n_code_links":1,"syntology":null},{"paper":null,"slug":"reffly-melody-constrained-lyrics-editing","title":"REFFLY: Melody-Constrained Lyrics Editing Model","date":"2024-08-30","arxiv_id":"2409.00292","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-ai-replace-human-subjects-a-large-scale","title":"Can Large Language Models Replace Human Subjects? A Large-Scale Replication of Scenario-Based Experiments in Psychology and Management","date":"2024-08-29","arxiv_id":"2409.00128","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-ai-driven-psychological","title":"Enhancing AI-Driven Psychological Consultation: Layered Prompts with Large Language Models","date":"2024-08-29","arxiv_id":"2408.16276","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-dialogue-generation-in-werewolf","title":"Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies","date":"2024-08-29","arxiv_id":"2408.16586","n_code_links":0,"syntology":null},{"paper":"/paper/privacylens-evaluating-privacy-norm-awareness","slug":"privacylens-evaluating-privacy-norm-awareness","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","date":"2024-08-29","arxiv_id":"2409.00138","n_code_links":1,"syntology":{"ran":13,"of":13,"n_ran_checked":9,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salt-nlp/privacylens"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"videollm-mod-efficient-video-language","title":"VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation","date":"2024-08-29","arxiv_id":"2408.16730","n_code_links":0,"syntology":null},{"paper":null,"slug":"aeroverse-uav-agent-benchmark-suite-for","title":"AeroVerse: UAV-Agent Benchmark Suite for Simulating, Pre-training, Finetuning, and Evaluating Aerospace Embodied World Models","date":"2024-08-28","arxiv_id":"2408.15511","n_code_links":0,"syntology":null},{"paper":null,"slug":"anvil-anomaly-based-vulnerability","title":"ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data","date":"2024-08-28","arxiv_id":"2408.16028","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-computational-representations-of","title":"Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark","date":"2024-08-28","arxiv_id":"2408.16131","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-named-entity-recognition-using-few","slug":"evaluating-named-entity-recognition-using-few","title":"Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language Models","date":"2024-08-28","arxiv_id":"2408.15796","n_code_links":1,"syntology":null},{"paper":null,"slug":"fractured-sorry-bench-framework-for-revealing","title":"FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)","date":"2024-08-28","arxiv_id":"2408.16163","n_code_links":0,"syntology":null},{"paper":"/paper/interactive-agents-simulating-counselor","slug":"interactive-agents-simulating-counselor","title":"Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions","date":"2024-08-28","arxiv_id":"2408.15787","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qiuhuachuan/interactive-agents"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/logic-enhanced-language-model-agents-for","slug":"logic-enhanced-language-model-agents-for","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","date":"2024-08-28","arxiv_id":"2408.16081","n_code_links":1,"syntology":null},{"paper":"/paper/unleashing-the-temporal-spatial-reasoning","slug":"unleashing-the-temporal-spatial-reasoning","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","date":"2024-08-28","arxiv_id":"2408.15876","n_code_links":1,"syntology":null},{"paper":null,"slug":"webpilot-a-versatile-and-autonomous-multi","title":"WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration","date":"2024-08-28","arxiv_id":"2408.15978","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-instruction-tuning-small-scale","title":"Multi-Modal Instruction-Tuning Small-Scale Language-and-Vision Assistant for Semiconductor Electron Micrograph Analysis","date":"2024-08-27","arxiv_id":"2409.07463","n_code_links":0,"syntology":null},{"paper":null,"slug":"negation-blindness-in-large-language-models","title":"Negation Blindness in Large Language Models: Unveiling the NO Syndrome in Image Generation","date":"2024-08-27","arxiv_id":"2409.00105","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameter-efficient-quantized-mixture-of","title":"Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis","date":"2024-08-27","arxiv_id":"2408.15305","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategic-optimization-and-challenges-of","title":"Strategic Optimization and Challenges of Large Language Models in Object-Oriented Programming","date":"2024-08-27","arxiv_id":"2408.14834","n_code_links":0,"syntology":null},{"paper":"/paper/the-mamba-in-the-llama-distilling-and","slug":"the-mamba-in-the-llama-distilling-and","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","date":"2024-08-27","arxiv_id":"2408.15237","n_code_links":2,"syntology":{"ran":9,"of":14,"n_ran_checked":7,"n_instrument":2,"unverified":5,"pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["itsdaniele/speculative_mamba","jxiw/mambainllama"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/toursynbio-a-multi-modal-large-model-and","slug":"toursynbio-a-multi-modal-large-model-and","title":"TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering","date":"2024-08-27","arxiv_id":"2408.15299","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-causality-manipulation-of-large","title":"Probing Causality Manipulation of Large Language Models","date":"2024-08-26","arxiv_id":"2408.14380","n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-aware-uncertainty-reduction-in-schema","title":"Prompt-Matcher: Leveraging Large Models to Reduce Uncertainty in Schema Matching Results","date":"2024-08-24","arxiv_id":"2408.14507","n_code_links":0,"syntology":null},{"paper":null,"slug":"iqa-eval-automatic-evaluation-of-human-model","title":"IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering","date":"2024-08-24","arxiv_id":"2408.13545","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilizing-large-language-models-for-named","title":"Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative Study","date":"2024-08-24","arxiv_id":"2408.13501","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-modeling-driven-large","title":"Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solving","date":"2024-08-23","arxiv_id":"2408.14494","n_code_links":0,"syntology":null},{"paper":"/paper/systematic-evaluation-of-llm-as-a-judge-in","slug":"systematic-evaluation-of-llm-as-a-judge-in","title":"Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates","date":"2024-08-23","arxiv_id":"2408.13006","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shenghh2015/llm-judge-eval"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-llms-understand-social-norms-in","title":"Can LLMs Understand Social Norms in Autonomous Driving Games?","date":"2024-08-22","arxiv_id":"2408.12680","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-based-automated-program-repair","title":"Enhancing Automated Program Repair with Solution Design","date":"2024-08-22","arxiv_id":"2408.12056","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-performance-how-compact-models","title":"Optimizing Performance: How Compact Models Match or Exceed GPT's Classification Capabilities through Fine-Tuning","date":"2024-08-22","arxiv_id":"2409.11408","n_code_links":0,"syntology":null},{"paper":null,"slug":"rulealign-making-large-language-models-better","title":"RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment","date":"2024-08-22","arxiv_id":"2408.12579","n_code_links":0,"syntology":null},{"paper":"/paper/towards-evaluating-and-building-versatile","slug":"towards-evaluating-and-building-versatile","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","date":"2024-08-22","arxiv_id":"2408.12547","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["magic-ai4med/meds-ins"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"burextract-llama-an-llm-for-clinical-concept","title":"BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports","date":"2024-08-21","arxiv_id":"2408.11334","n_code_links":0,"syntology":null},{"paper":null,"slug":"d-rmgpt-robot-assisted-collaborative-tasks","title":"D-RMGPT: Robot-assisted collaborative tasks driven by large multimodal models","date":"2024-08-21","arxiv_id":"2408.11761","n_code_links":0,"syntology":null},{"paper":"/paper/doctabqa-answering-questions-from-long","slug":"doctabqa-answering-questions-from-long","title":"DocTabQA: Answering Questions from Long Documents Using Tables","date":"2024-08-21","arxiv_id":"2408.11490","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-feature","title":"Exploring Large Language Models for Feature Selection: A Data-centric Perspective","date":"2024-08-21","arxiv_id":"2408.12025","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-fine-tuned-retrieval-augmented","slug":"leveraging-fine-tuned-retrieval-augmented","title":"Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards","date":"2024-08-21","arxiv_id":"2408.11775","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-evaluating-large-language-models-on","title":"SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding","date":"2024-08-21","arxiv_id":"2408.11319","n_code_links":0,"syntology":null},{"paper":null,"slug":"crafting-tomorrow-s-headlines-neural-news","title":"Crafting Tomorrow's Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian","date":"2024-08-20","arxiv_id":"2408.10724","n_code_links":0,"syntology":null},{"paper":null,"slug":"dr-academy-a-benchmark-for-evaluating","title":"Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models","date":"2024-08-20","arxiv_id":"2408.10947","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-well-do-large-language-models-serve-as","title":"How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?","date":"2024-08-20","arxiv_id":"2408.10495","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-finllms-open-multimodal-large-language","title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","date":"2024-08-20","arxiv_id":"2408.11878","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-verilogeval-newer-llms-in-context","slug":"revisiting-verilogeval-newer-llms-in-context","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","date":"2024-08-20","arxiv_id":"2408.11053","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["nvlabs/verilog-eval"],"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/soda-eval-open-domain-dialogue-evaluation-in","slug":"soda-eval-open-domain-dialogue-evaluation-in","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","date":"2024-08-20","arxiv_id":"2408.10902","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-llms-for-translating-classical","title":"Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving","date":"2024-08-19","arxiv_id":"2408.09945","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-cloud-collaborative-motion-planning-for","title":"Edge-Cloud Collaborative Motion Planning for Autonomous Driving with Large Language Models","date":"2024-08-19","arxiv_id":"2408.09972","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-directed-turing-test-for-large-language","title":"Self-Directed Turing Test for Large Language Models","date":"2024-08-19","arxiv_id":"2408.09853","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-distribution-generalization-via-1","slug":"out-of-distribution-generalization-via-1","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","date":"2024-08-18","arxiv_id":"2408.09503","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiajunsong629/ood-generalization-via-composition"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sentiment-analysis-of-preservice-teachers","title":"Sentiment analysis of preservice teachers' reflections using a large language model","date":"2024-08-17","arxiv_id":"2408.11862","n_code_links":0,"syntology":null},{"paper":null,"slug":"tablebench-a-comprehensive-and-complex","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","date":"2024-08-17","arxiv_id":"2408.09174","n_code_links":0,"syntology":null},{"paper":null,"slug":"unraveling-text-generation-in-llms-a","title":"Unraveling Text Generation in LLMs: A Stochastic Differential Equation Approach","date":"2024-08-17","arxiv_id":"2408.11863","n_code_links":0,"syntology":null}],"record_sha256":"95deb573ff19639dba0808eeac6b48799d9d01f0b1c9b79f0889a6a8fcc191d2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}