{"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-3/papers/2","list_of":"/method/gpt-3","method":"GPT-3","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":2,"pages_in_order":20,"rows_per_page":100,"rows":[101,200],"of":1906,"counts":{"archive_papers_tagged":1906,"with_a_code_link":866,"where_syntology_ran_a_sample":319,"not_listed_spam_title":0,"listed":1906,"listed_where_code_ran":319,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":259,"every_run_a_failure_of_syntologys_instrument":60,"listed_with_a_run_with_no_instrument_failure":259,"listed_every_run_a_failure_of_syntologys_instrument":60,"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-3","prev":"/method/gpt-3","next":"/method/gpt-3/papers/3","papers":[{"paper":null,"slug":"divide-then-aggregate-an-efficient-tool","title":"Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation","date":"2025-01-21","arxiv_id":"2501.12432","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-data-can-mislead-evaluations","title":"Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection","date":"2025-01-20","arxiv_id":"2501.11786","n_code_links":0,"syntology":null},{"paper":null,"slug":"trustformer-a-trusted-federated-transformer","title":"Trustformer: A Trusted Federated Transformer","date":"2025-01-20","arxiv_id":"2501.11706","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-arabic-text-to-puzzles-llm-driven","title":"From Arabic Text to Puzzles: LLM-Driven Development of Arabic Educational Crosswords","date":"2025-01-19","arxiv_id":"2501.11035","n_code_links":0,"syntology":null},{"paper":"/paper/bias-in-decision-making-for-ai-s-ethical","slug":"bias-in-decision-making-for-ai-s-ethical","title":"Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude","date":"2025-01-17","arxiv_id":"2501.10484","n_code_links":1,"syntology":null},{"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":"the-impact-of-big-five-personality-traits-on","title":"The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study","date":"2025-01-15","arxiv_id":"2503.15497","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":"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":"large-language-models-for-mental-health-1","title":"Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case","date":"2025-01-02","arxiv_id":"2501.01305","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-the-performance-of-black-box-llms","slug":"predicting-the-performance-of-black-box-llms","title":"Predicting the Performance of Black-box LLMs through Self-Queries","date":"2025-01-02","arxiv_id":"2501.01558","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dsam99/quere"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":"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":null,"slug":"sentiment-trading-with-large-language-models","title":"Sentiment trading with large language models","date":"2024-12-26","arxiv_id":"2412.19245","n_code_links":0,"syntology":null},{"paper":null,"slug":"saflite-fuzzing-autonomous-systems-via-large","title":"SAFLITE: Fuzzing Autonomous Systems via Large Language Models","date":"2024-12-25","arxiv_id":"2412.18727","n_code_links":0,"syntology":null},{"paper":null,"slug":"whose-morality-do-they-speak-unraveling","title":"Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models","date":"2024-12-25","arxiv_id":"2412.18863","n_code_links":0,"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":"assessing-social-alignment-do-personality","title":"Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?","date":"2024-12-21","arxiv_id":"2412.16772","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-obfuscate-code-a-systematic-analysis","title":"Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation","date":"2024-12-20","arxiv_id":"2412.16135","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-readable-adversarial-prompts-an","title":"Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context","date":"2024-12-20","arxiv_id":"2412.16359","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":"/paper/tomg-bench-evaluating-llms-on-text-based-open","slug":"tomg-bench-evaluating-llms-on-text-based-open","title":"TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation","date":"2024-12-19","arxiv_id":"2412.14642","n_code_links":1,"syntology":null},{"paper":"/paper/autonomous-microscopy-experiments-through","slug":"autonomous-microscopy-experiments-through","title":"Autonomous Microscopy Experiments through Large Language Model Agents","date":"2024-12-18","arxiv_id":"2501.10385","n_code_links":1,"syntology":null},{"paper":"/paper/glimpse-enabling-white-box-methods-to-use","slug":"glimpse-enabling-white-box-methods-to-use","title":"Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection","date":"2024-12-16","arxiv_id":"2412.11506","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["baoguangsheng/glimpse"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"reasoner-outperforms-generative-stance","title":"Reasoner Outperforms: Generative Stance Detection with Rationalization for Social Media","date":"2024-12-13","arxiv_id":"2412.10266","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":"auto-generating-earnings-report-analysis-via","title":"Auto-Generating Earnings Report Analysis via a Financial-Augmented LLM","date":"2024-12-11","arxiv_id":"2412.08179","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-the-index-gradients-for","slug":"exploiting-the-index-gradients-for","title":"Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models","date":"2024-12-11","arxiv_id":"2412.08615","n_code_links":1,"syntology":null},{"paper":null,"slug":"graphtool-instruction-revolutionizing-graph","title":"GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction","date":"2024-12-11","arxiv_id":"2412.12152","n_code_links":0,"syntology":null},{"paper":null,"slug":"imitate-before-detect-aligning-machine","title":"Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection","date":"2024-12-11","arxiv_id":"2412.10432","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-still-face-challenges","title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge","date":"2024-12-11","arxiv_id":"2412.08317","n_code_links":0,"syntology":null},{"paper":"/paper/intellectseeker-a-personalized-literature","slug":"intellectseeker-a-personalized-literature","title":"IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model","date":"2024-12-10","arxiv_id":"2412.07213","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-multi-task-learning-for-enhanced","title":"Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models","date":"2024-12-09","arxiv_id":"2412.06249","n_code_links":0,"syntology":null},{"paper":"/paper/m-3-20m-a-large-scale-multi-modal-molecule","slug":"m-3-20m-a-large-scale-multi-modal-molecule","title":"M$^{3}$-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery","date":"2024-12-08","arxiv_id":"2412.06847","n_code_links":1,"syntology":null},{"paper":null,"slug":"100-hallucination-elimination-using-acurai","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","date":"2024-12-06","arxiv_id":"2412.05223","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-good-is-chatgpt-in-giving-adaptive","title":"How Good is ChatGPT in Giving Adaptive Guidance Using Knowledge Graphs in E-Learning Environments?","date":"2024-12-05","arxiv_id":"2412.03856","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-the-mutation-in-large-language","title":"Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms","date":"2024-12-04","arxiv_id":"2412.03250","n_code_links":0,"syntology":null},{"paper":null,"slug":"cognitive-biases-in-large-language-models-a","title":"Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments","date":"2024-11-30","arxiv_id":"2412.00323","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-the-deaf-and-hard-of-hearing","title":"Empowering the Deaf and Hard of Hearing Community: Enhancing Video Captions Using Large Language Models","date":"2024-11-30","arxiv_id":"2412.00342","n_code_links":0,"syntology":null},{"paper":null,"slug":"forma-mentis-networks-predict-creativity","title":"Forma mentis networks predict creativity ratings of short texts via interpretable artificial intelligence in human and GPT-simulated raters","date":"2024-11-30","arxiv_id":"2412.00530","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-prompt-generation-and-grounding","title":"Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection","date":"2024-11-28","arxiv_id":"2411.19220","n_code_links":0,"syntology":null},{"paper":"/paper/deniahl-in-context-features-influence-llm","slug":"deniahl-in-context-features-influence-llm","title":"DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities","date":"2024-11-28","arxiv_id":"2411.19360","n_code_links":1,"syntology":null},{"paper":null,"slug":"smartllmsentry-a-comprehensive-llm-based","title":"SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework","date":"2024-11-28","arxiv_id":"2411.19234","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-example-selection-in-few-shot","title":"The Impact of Example Selection in Few-Shot Prompting on Automated Essay Scoring Using GPT Models","date":"2024-11-28","arxiv_id":"2411.18924","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-literature-review-using-nlp","title":"Automated Literature Review Using NLP Techniques and LLM-Based Retrieval-Augmented Generation","date":"2024-11-27","arxiv_id":"2411.18583","n_code_links":0,"syntology":null},{"paper":"/paper/drs-deep-question-reformulation-with","slug":"drs-deep-question-reformulation-with","title":"DRS: Deep Question Reformulation With Structured Output","date":"2024-11-27","arxiv_id":"2411.17993","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-evaluating-language-models-with","slug":"training-and-evaluating-language-models-with","title":"Training and Evaluating Language Models with Template-based Data Generation","date":"2024-11-27","arxiv_id":"2411.18104","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: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["iiis-ai/templatemath"],"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":"can-artificial-intelligence-predict-clinical","title":"Can artificial intelligence predict clinical trial outcomes?","date":"2024-11-26","arxiv_id":"2411.17595","n_code_links":0,"syntology":null},{"paper":null,"slug":"give-me-the-code-log-analysis-of-first-year","title":"\"Give me the code\" -- Log Analysis of First-Year CS Students' Interactions With GPT","date":"2024-11-26","arxiv_id":"2411.17855","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-ai-grade-your-essays-a-comparative","title":"Can AI grade your essays? A comparative analysis of large language models and teacher ratings in multidimensional essay scoring","date":"2024-11-25","arxiv_id":"2411.16337","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-llms-with-noisy-data-for","title":"Fine-Tuning LLMs with Noisy Data for Political Argument Generation and Post Guidance","date":"2024-11-25","arxiv_id":"2411.16813","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatbci-a-p300-speller-bci-leveraging-large","title":"ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios","date":"2024-11-23","arxiv_id":"2411.15395","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-combined-encoder-and-transformer-approach","title":"A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation","date":"2024-11-19","arxiv_id":"2411.12157","n_code_links":0,"syntology":null},{"paper":null,"slug":"chapter-7-review-of-data-driven-generative-ai","title":"Chapter 7 Review of Data-Driven Generative AI Models for Knowledge Extraction from Scientific Literature in Healthcare","date":"2024-11-18","arxiv_id":"2411.11635","n_code_links":0,"syntology":null},{"paper":"/paper/perfcodegen-improving-performance-of-llm","slug":"perfcodegen-improving-performance-of-llm","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","date":"2024-11-18","arxiv_id":"2412.03578","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["SalesforceAIResearch/perfcodegen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"understanding-student-sentiment-on-mental","title":"Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models","date":"2024-11-18","arxiv_id":"2412.04326","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-prompt-formatting-have-any-impact-on-llm","title":"Does Prompt Formatting Have Any Impact on LLM Performance?","date":"2024-11-15","arxiv_id":"2411.10541","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-and-fine-tuning-large-language","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","date":"2024-11-15","arxiv_id":"2411.10129","n_code_links":0,"syntology":null},{"paper":null,"slug":"hategpt-unleashing-gpt-3-5-turbo-to-combat","title":"HateGPT: Unleashing GPT-3.5 Turbo to Combat Hate Speech on X","date":"2024-11-14","arxiv_id":"2411.09214","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmstinger-jailbreaking-llms-using-rl-fine","title":"LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs","date":"2024-11-13","arxiv_id":"2411.08862","n_code_links":0,"syntology":null},{"paper":null,"slug":"responsible-ai-in-construction-safety","title":"Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering","date":"2024-11-13","arxiv_id":"2411.08320","n_code_links":0,"syntology":null},{"paper":null,"slug":"valtest-automated-validation-of-language","title":"VALTEST: Automated Validation of Language Model Generated Test Cases","date":"2024-11-13","arxiv_id":"2411.08254","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-chatgpt-3-5-efficiency-in-solving","slug":"evaluating-chatgpt-3-5-efficiency-in-solving","title":"Evaluating ChatGPT-3.5 Efficiency in Solving Coding Problems of Different Complexity Levels: An Empirical Analysis","date":"2024-11-12","arxiv_id":"2411.07529","n_code_links":1,"syntology":null},{"paper":"/paper/fair-summarization-bridging-quality-and","slug":"fair-summarization-bridging-quality-and","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","date":"2024-11-12","arxiv_id":"2411.07521","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["PortNLP/FairEXTSummarizer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"ambient-ai-scribing-support-comparing-the","title":"Ambient AI Scribing Support: Comparing the Performance of Specialized AI Agentic Architecture to Leading Foundational Models","date":"2024-11-11","arxiv_id":"2411.06713","n_code_links":0,"syntology":null},{"paper":null,"slug":"cancer-answer-empowering-cancer-care-with","title":"Cancer-Answer: Empowering Cancer Care with Advanced Large Language Models","date":"2024-11-11","arxiv_id":"2411.06946","n_code_links":0,"syntology":null},{"paper":null,"slug":"neko-toward-post-recognition-generative","title":"NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts","date":"2024-11-08","arxiv_id":"2411.05945","n_code_links":0,"syntology":null},{"paper":"/paper/finetunebench-how-well-do-commercial-fine","slug":"finetunebench-how-well-do-commercial-fine","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","date":"2024-11-07","arxiv_id":"2411.05059","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrievegpt-merging-prompts-and-mathematical","title":"RetrieveGPT: Merging Prompts and Mathematical Models for Enhanced Code-Mixed Information Retrieval","date":"2024-11-07","arxiv_id":"2411.04752","n_code_links":0,"syntology":null},{"paper":null,"slug":"stand-guard-a-small-task-adaptive-content","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","date":"2024-11-07","arxiv_id":"2411.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-recent-large-language","title":"A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients","date":"2024-11-06","arxiv_id":"2411.03805","n_code_links":0,"syntology":null},{"paper":null,"slug":"phdgpt-introducing-a-psychometric-and","title":"PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology","date":"2024-11-06","arxiv_id":"2411.10473","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","n_code_links":0,"syntology":null},{"paper":null,"slug":"youtube-comments-decoded-leveraging-llms-for","title":"YouTube Comments Decoded: Leveraging LLMs for Low Resource Language Classification","date":"2024-11-06","arxiv_id":"2411.05039","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-and-limitations-of-llms-in","title":"Advancements and limitations of LLMs in replicating human color-word associations","date":"2024-11-04","arxiv_id":"2411.02116","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-emotional-descriptions-to","title":"Grounding Emotional Descriptions to Electrovibration Haptic Signals","date":"2024-11-04","arxiv_id":"2411.02118","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-lab-test-results-on","title":"Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes","date":"2024-11-01","arxiv_id":"2411.02523","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-a-game-changer-for-software-engineers","title":"LLMs: A Game-Changer for Software Engineers?","date":"2024-11-01","arxiv_id":"2411.00932","n_code_links":0,"syntology":null},{"paper":"/paper/selfcodealign-self-alignment-for-code","slug":"selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","arxiv_id":"2410.24198","n_code_links":2,"syntology":{"ran":30,"of":37,"n_ran_checked":22,"n_instrument":8,"unverified":7,"pointer_only":0,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["bigcode-project/selfcodealign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["community","listed","official"]}}},{"paper":null,"slug":"a-comprehensive-study-on-quantization","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","date":"2024-10-30","arxiv_id":"2411.02530","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-choice-in-ordered-bundles","title":"Sequential choice in ordered bundles","date":"2024-10-29","arxiv_id":"2410.21670","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-yet-effective-corpus-construction-1","slug":"a-simple-yet-effective-corpus-construction-1","title":"A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction","date":"2024-10-28","arxiv_id":"2410.20838","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-gpt-4-less-politically-biased-than-gpt-3-5","title":"Is GPT-4 Less Politically Biased than GPT-3.5? A Renewed Investigation of ChatGPT's Political Biases","date":"2024-10-28","arxiv_id":"2410.21008","n_code_links":0,"syntology":null},{"paper":null,"slug":"stealthy-jailbreak-attacks-on-large-language","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","date":"2024-10-28","arxiv_id":"2410.21083","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-large-language-model-based-hyper","slug":"sequential-large-language-model-based-hyper","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","date":"2024-10-27","arxiv_id":"2410.20302","n_code_links":1,"syntology":null},{"paper":null,"slug":"think-carefully-and-check-again-meta","title":"Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization","date":"2024-10-26","arxiv_id":"2410.20021","n_code_links":0,"syntology":null},{"paper":"/paper/iterative-self-tuning-llms-for-enhanced","slug":"iterative-self-tuning-llms-for-enhanced","title":"Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities","date":"2024-10-24","arxiv_id":"2410.18469","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-up-masked-diffusion-models-on-text","slug":"scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","arxiv_id":"2410.18514","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["ml-gsai/smdm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scattered-forest-search-smarter-code-space","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","date":"2024-10-22","arxiv_id":"2411.05010","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-system-for-automatic-map","slug":"an-efficient-system-for-automatic-map","title":"An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps","date":"2024-10-21","arxiv_id":"2410.15780","n_code_links":1,"syntology":null},{"paper":null,"slug":"guardians-of-discourse-evaluating-llms-on","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","date":"2024-10-21","arxiv_id":"2410.15623","n_code_links":0,"syntology":null},{"paper":"/paper/on-creating-an-english-thai-code-switched","slug":"on-creating-an-english-thai-code-switched","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","date":"2024-10-21","arxiv_id":"2410.16221","n_code_links":1,"syntology":null},{"paper":"/paper/brief-bridging-retrieval-and-inference-for","slug":"brief-bridging-retrieval-and-inference-for","title":"BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression","date":"2024-10-20","arxiv_id":"2410.15277","n_code_links":1,"syntology":null},{"paper":"/paper/does-chatgpt-have-a-poetic-style","slug":"does-chatgpt-have-a-poetic-style","title":"Does ChatGPT Have a Poetic Style?","date":"2024-10-20","arxiv_id":"2410.15299","n_code_links":1,"syntology":null},{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"phrase":"9 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; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/faithbench-a-diverse-hallucination-benchmark","slug":"faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","n_code_links":2,"syntology":null},{"paper":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","n_code_links":1,"syntology":null},{"paper":null,"slug":"jailbreaking-llm-controlled-robots","title":"Jailbreaking LLM-Controlled Robots","date":"2024-10-17","arxiv_id":"2410.13691","n_code_links":0,"syntology":null}],"record_sha256":"a268b8f06aa983e44bd15c56e439c7f6e1b2ca459825af10c8db7c13a8e54501","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}