{"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/discriminative-fine-tuning/papers/6","list_of":"/method/discriminative-fine-tuning","method":"Discriminative Fine-Tuning","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":6,"pages_in_order":20,"rows_per_page":100,"rows":[501,600],"of":1990,"counts":{"archive_papers_tagged":1990,"with_a_code_link":794,"where_syntology_ran_a_sample":271,"not_listed_spam_title":0,"listed":1990,"listed_where_code_ran":271,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":223,"every_run_a_failure_of_syntologys_instrument":48,"listed_with_a_run_with_no_instrument_failure":223,"listed_every_run_a_failure_of_syntologys_instrument":48,"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/discriminative-fine-tuning","prev":"/method/discriminative-fine-tuning/papers/5","next":"/method/discriminative-fine-tuning/papers/7","papers":[{"paper":null,"slug":"enhancing-multi-hop-reasoning-through","title":"Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing","date":"2024-08-22","arxiv_id":"2408.12456","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":"applying-and-evaluating-large-language-models","title":"Applying and Evaluating Large Language Models in Mental Health Care: A Scoping Review of Human-Assessed Generative Tasks","date":"2024-08-21","arxiv_id":"2408.11288","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":null,"slug":"mixed-sparsity-training-achieving-4-times","title":"Mixed Sparsity Training: Achieving 4$\\times$ FLOP Reduction for Transformer Pretraining","date":"2024-08-21","arxiv_id":"2408.11746","n_code_links":0,"syntology":null},{"paper":"/paper/language-modeling-on-tabular-data-a-survey-of","slug":"language-modeling-on-tabular-data-a-survey-of","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","date":"2024-08-20","arxiv_id":"2408.10548","n_code_links":1,"syntology":null},{"paper":null,"slug":"tracing-privacy-leakage-of-language-models-to","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","date":"2024-08-20","arxiv_id":"2408.10468","n_code_links":0,"syntology":null},{"paper":"/paper/while-github-copilot-excels-at-coding-does-it","slug":"while-github-copilot-excels-at-coding-does-it","title":"Security Attacks on LLM-based Code Completion Tools","date":"2024-08-20","arxiv_id":"2408.11006","n_code_links":1,"syntology":null},{"paper":"/paper/enhance-lifelong-model-editing-with","slug":"enhance-lifelong-model-editing-with","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","date":"2024-08-19","arxiv_id":"2408.11869","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-augmented-reinforcement-learning-with","title":"GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching","date":"2024-08-19","arxiv_id":"2408.10286","n_code_links":0,"syntology":null},{"paper":null,"slug":"rhyme-aware-chinese-lyric-generator-based-on","title":"Rhyme-aware Chinese lyric generator based on GPT","date":"2024-08-19","arxiv_id":"2408.10130","n_code_links":0,"syntology":null},{"paper":null,"slug":"tba-faster-large-language-model-training","title":"SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training","date":"2024-08-19","arxiv_id":"2408.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversum-a-contrastive-learning-based","title":"ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents","date":"2024-08-17","arxiv_id":"2408.09273","n_code_links":0,"syntology":null},{"paper":"/paper/the-fellowship-of-the-llms-multi-agent","slug":"the-fellowship-of-the-llms-multi-agent","title":"The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation","date":"2024-08-16","arxiv_id":"2408.08688","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-and-large-language-models-for-1","title":"Transformers and Large Language Models for Efficient Intrusion Detection Systems: A Comprehensive Survey","date":"2024-08-14","arxiv_id":"2408.07583","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-for-automatic-topic-labelling","title":"Generative AI for automatic topic labelling","date":"2024-08-13","arxiv_id":"2408.07003","n_code_links":0,"syntology":null},{"paper":null,"slug":"pragmatic-inference-of-scalar-implicature-by","title":"Pragmatic inference of scalar implicature by LLMs","date":"2024-08-13","arxiv_id":"2408.06673","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-whisper-s-recognition-performance","title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","date":"2024-08-10","arxiv_id":"2408.05554","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-text-to-insight-leveraging-large","title":"From Text to Insight: Leveraging Large Language Models for Performance Evaluation in Management","date":"2024-08-09","arxiv_id":"2408.05328","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-code-completion-for-local","title":"Retrieval-augmented code completion for local projects using large language models","date":"2024-08-09","arxiv_id":"2408.05026","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-explainer-interactive-learning-of","slug":"transformer-explainer-interactive-learning-of","title":"Transformer Explainer: Interactive Learning of Text-Generative Models","date":"2024-08-08","arxiv_id":"2408.04619","n_code_links":1,"syntology":null},{"paper":"/paper/image-to-latex-converter-for-mathematical","slug":"image-to-latex-converter-for-mathematical","title":"Image-to-LaTeX Converter for Mathematical Formulas and Text","date":"2024-08-07","arxiv_id":"2408.04015","n_code_links":1,"syntology":null},{"paper":"/paper/is-child-directed-speech-effective-training","slug":"is-child-directed-speech-effective-training","title":"Is Child-Directed Speech Effective Training Data for Language Models?","date":"2024-08-07","arxiv_id":"2408.03617","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["styfeng/tinydialogues"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"socfedgpt-federated-gpt-based-adaptive","title":"SocFedGPT: Federated GPT-based Adaptive Content Filtering System Leveraging User Interactions in Social Networks","date":"2024-08-07","arxiv_id":"2408.05243","n_code_links":0,"syntology":null},{"paper":"/paper/2408-02946","slug":"2408-02946","title":"Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws","date":"2024-08-06","arxiv_id":"2408.02946","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":5,"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) · 4 unverified","official":{"repos":["alignmentresearch/scaling-poisoning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2408-03119","title":"Evaluating the Translation Performance of Large Language Models Based on Euas-20","date":"2024-08-06","arxiv_id":"2408.03119","n_code_links":0,"syntology":null},{"paper":null,"slug":"flash-federated-learning-based-llms-for","title":"FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG","date":"2024-08-06","arxiv_id":"2408.05242","n_code_links":0,"syntology":null},{"paper":"/paper/trafficgpt-an-llm-approach-for-open-set","slug":"trafficgpt-an-llm-approach-for-open-set","title":"TrafficGPT: An LLM Approach for Open-Set Encrypted Traffic Classification","date":"2024-08-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/2408-01966","slug":"2408-01966","title":"ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science","date":"2024-08-04","arxiv_id":"2408.01966","n_code_links":1,"syntology":null},{"paper":"/paper/2408-02001","slug":"2408-02001","title":"AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis","date":"2024-08-04","arxiv_id":"2408.02001","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-01614","title":"Advancing Mental Health Pre-Screening: A New Custom GPT for Psychological Distress Assessment","date":"2024-08-03","arxiv_id":"2408.01614","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01866","title":"Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly","date":"2024-08-03","arxiv_id":"2408.01866","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-comes-after-transformers-a-selective","title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","date":"2024-08-01","arxiv_id":"2408.00386","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21330","title":"Performance of Recent Large Language Models for a Low-Resourced Language","date":"2024-07-31","arxiv_id":"2407.21330","n_code_links":0,"syntology":null},{"paper":"/paper/2407-21491","slug":"2407-21491","title":"Generative Expressive Conversational Speech Synthesis","date":"2024-07-31","arxiv_id":"2407.21491","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-00197","title":"Automated Software Vulnerability Static Code Analysis Using Generative Pre-Trained Transformer Models","date":"2024-07-31","arxiv_id":"2408.00197","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-and-llms-based-avgfp-brightness","title":"BERT and LLMs-Based avGFP Brightness Prediction and Mutation Design","date":"2024-07-30","arxiv_id":"2407.20534","n_code_links":0,"syntology":null},{"paper":null,"slug":"ageval-a-benchmark-for-zero-shot-and-few-shot","title":"AgEval: A Benchmark for Zero-Shot and Few-Shot Plant Stress Phenotyping with Multimodal LLMs","date":"2024-07-29","arxiv_id":"2407.19617","n_code_links":0,"syntology":null},{"paper":"/paper/autoscale-automatic-prediction-of-compute","slug":"autoscale-automatic-prediction-of-compute","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","date":"2024-07-29","arxiv_id":"2407.20177","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":["feiyang-k/autoscale"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/detecting-and-understanding-vulnerabilities","slug":"detecting-and-understanding-vulnerabilities","title":"Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability","date":"2024-07-29","arxiv_id":"2407.19842","n_code_links":1,"syntology":null},{"paper":null,"slug":"adacoder-adaptive-prompt-compression-for","title":"AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering","date":"2024-07-28","arxiv_id":"2407.19410","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-generative-ai-an-existential-threat-to","title":"Is Generative AI an Existential Threat to Human Creatives? Insights from Financial Economics","date":"2024-07-28","arxiv_id":"2407.19586","n_code_links":0,"syntology":null},{"paper":"/paper/motamot-a-dataset-for-revealing-the-supremacy","slug":"motamot-a-dataset-for-revealing-the-supremacy","title":"Motamot: A Dataset for Revealing the Supremacy of Large Language Models over Transformer Models in Bengali Political Sentiment Analysis","date":"2024-07-28","arxiv_id":"2407.19528","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-reliable-common-sense-reasoning-socialbot","title":"A Reliable Common-Sense Reasoning Socialbot Built Using LLMs and Goal-Directed ASP","date":"2024-07-26","arxiv_id":"2407.18498","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-artificial-intelligence-teaming-for","title":"Human-artificial intelligence teaming for scientific information extraction from data-driven additive manufacturing research using large language models","date":"2024-07-26","arxiv_id":"2407.18827","n_code_links":0,"syntology":null},{"paper":"/paper/is-larger-always-better-evaluating-and","slug":"is-larger-always-better-evaluating-and","title":"ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks","date":"2024-07-26","arxiv_id":"2407.18525","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yhzhu99/ehr-llm-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/personagym-evaluating-persona-agents-and-llms","slug":"personagym-evaluating-persona-agents-and-llms","title":"PersonaGym: Evaluating Persona Agents and LLMs","date":"2024-07-25","arxiv_id":"2407.18416","n_code_links":1,"syntology":null},{"paper":null,"slug":"testing-large-language-models-on-driving","title":"Testing Large Language Models on Driving Theory Knowledge and Skills for Connected Autonomous Vehicles","date":"2024-07-24","arxiv_id":"2407.17211","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-polysemy-evolution-using","title":"Analyzing Polysemy Evolution Using Semantic Cells","date":"2024-07-23","arxiv_id":"2407.16110","n_code_links":0,"syntology":null},{"paper":null,"slug":"impacts-of-anthropomorphizing-large-language","title":"Impacts of Anthropomorphizing Large Language Models in Learning Environments","date":"2024-07-22","arxiv_id":"2408.03945","n_code_links":0,"syntology":null},{"paper":"/paper/inverted-activations","slug":"inverted-activations","title":"Inverted Activations: Reducing Memory Footprint in Neural Network Training","date":"2024-07-22","arxiv_id":"2407.15545","n_code_links":1,"syntology":null},{"paper":"/paper/decoding-multilingual-moral-preferences","slug":"decoding-multilingual-moral-preferences","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","date":"2024-07-21","arxiv_id":"2407.15184","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","n_code_links":2,"syntology":{"ran":5,"of":8,"n_ran_checked":3,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-open-source-llms-compete-with-commercial","slug":"can-open-source-llms-compete-with-commercial","title":"Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2024-07-18","arxiv_id":"2407.13511","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-for-anxiety","slug":"evaluating-large-language-models-for-anxiety","title":"Evaluating Large Language Models for Anxiety and Depression Classification using Counseling and Psychotherapy Transcripts","date":"2024-07-18","arxiv_id":"2407.13228","n_code_links":1,"syntology":null},{"paper":"/paper/werewolf-arena-a-case-study-in-llm-evaluation","slug":"werewolf-arena-a-case-study-in-llm-evaluation","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","date":"2024-07-18","arxiv_id":"2407.13943","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":["google/werewolf_arena"],"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":"beyond-binary-multiclass-paraphasia-detection","title":"Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models","date":"2024-07-16","arxiv_id":"2407.11345","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatbcg-can-ai-read-your-slide-deck","title":"ChatBCG: Can AI Read Your Slide Deck?","date":"2024-07-16","arxiv_id":"2407.12875","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-assisted-annotation-of-rhetorical-and","title":"GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text","date":"2024-07-16","arxiv_id":"2407.11827","n_code_links":0,"syntology":null},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/trust-no-bot-discovering-personal-disclosures","slug":"trust-no-bot-discovering-personal-disclosures","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","date":"2024-07-16","arxiv_id":"2407.11438","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-llms-for-verilog-generation","title":"CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization","date":"2024-07-15","arxiv_id":"2407.10424","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-new-connections-llms-as-puzzle","title":"Making New Connections: LLMs as Puzzle Generators for The New York Times' Connections Word Game","date":"2024-07-15","arxiv_id":"2407.11240","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-interpretability-of-large","title":"Mechanistic interpretability of large language models with applications to the financial services industry","date":"2024-07-15","arxiv_id":"2407.11215","n_code_links":0,"syntology":null},{"paper":"/paper/metallm-a-high-performant-and-cost-efficient","slug":"metallm-a-high-performant-and-cost-efficient","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","date":"2024-07-15","arxiv_id":"2407.10834","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":["mail-research/metallm-wrapper"],"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":"curriculum-learning-for-small-code-language","title":"Curriculum Learning for Small Code Language Models","date":"2024-07-14","arxiv_id":"2407.10194","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-level-clinical-entity-and-relation","title":"Document-level Clinical Entity and Relation Extraction via Knowledge Base-Guided Generation","date":"2024-07-13","arxiv_id":"2407.10021","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-in-store-customer-journeys-from","title":"Generating In-store Customer Journeys from Scratch with GPT Architectures","date":"2024-07-13","arxiv_id":"2407.11081","n_code_links":0,"syntology":null},{"paper":"/paper/astprompter-weakly-supervised-automated","slug":"astprompter-weakly-supervised-automated","title":"ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts","date":"2024-07-12","arxiv_id":"2407.09447","n_code_links":1,"syntology":null},{"paper":"/paper/show-don-t-tell-evaluating-large-language","slug":"show-don-t-tell-evaluating-large-language","title":"Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay","date":"2024-07-12","arxiv_id":"2407.11068","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-automatic-group-membership-annotation","title":"Toward Automatic Group Membership Annotation for Group Fairness Evaluation","date":"2024-07-12","arxiv_id":"2407.08926","n_code_links":0,"syntology":null},{"paper":"/paper/mavis-mathematical-visual-instruction-tuning","slug":"mavis-mathematical-visual-instruction-tuning","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","date":"2024-07-11","arxiv_id":"2407.08739","n_code_links":3,"syntology":null},{"paper":null,"slug":"on-the-in-security-of-llm-app-stores","title":"On the (In)Security of LLM App Stores","date":"2024-07-11","arxiv_id":"2407.08422","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-time-anomaly-detection-and-reactive","title":"Real-Time Anomaly Detection and Reactive Planning with Large Language Models","date":"2024-07-11","arxiv_id":"2407.08735","n_code_links":0,"syntology":null},{"paper":"/paper/kpopmt-translation-dataset-with-terminology","slug":"kpopmt-translation-dataset-with-terminology","title":"KpopMT: Translation Dataset with Terminology for Kpop Fandom","date":"2024-07-10","arxiv_id":"2407.07413","n_code_links":1,"syntology":null},{"paper":"/paper/rosa-random-subspace-adaptation-for-efficient","slug":"rosa-random-subspace-adaptation-for-efficient","title":"ROSA: Random Subspace Adaptation for Efficient Fine-Tuning","date":"2024-07-10","arxiv_id":"2407.07802","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-sustainability-intention-of-esg","title":"Measuring Sustainability Intention of ESG Fund Disclosure using Few-Shot Learning","date":"2024-07-09","arxiv_id":"2407.06893","n_code_links":0,"syntology":null},{"paper":null,"slug":"raply-a-profanity-mitigated-rap-generator","title":"Raply: A profanity-mitigated rap generator","date":"2024-07-09","arxiv_id":"2407.06941","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-general-natural-language-description","title":"Solving General Natural-Language-Description Optimization Problems with Large Language Models","date":"2024-07-09","arxiv_id":"2407.07924","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-pretrained-large-language-model-with","title":"Using Pretrained Large Language Model with Prompt Engineering to Answer Biomedical Questions","date":"2024-07-09","arxiv_id":"2407.06779","n_code_links":0,"syntology":null},{"paper":null,"slug":"potential-of-multimodal-large-language-models","title":"Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports","date":"2024-07-08","arxiv_id":"2407.05758","n_code_links":0,"syntology":null},{"paper":null,"slug":"surprising-gender-biases-in-gpt","title":"Surprising gender biases in GPT","date":"2024-07-08","arxiv_id":"2407.06003","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-vs-retro-exploring-the-intersection-of","title":"GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning","date":"2024-07-05","arxiv_id":"2407.04528","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-analysis-prompting-improves-llm","title":"Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks","date":"2024-07-04","arxiv_id":"2407.03624","n_code_links":0,"syntology":null},{"paper":null,"slug":"slice-100k-a-multimodal-dataset-for-extrusion","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","date":"2024-07-04","arxiv_id":"2407.04180","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-gradient-descent-with-generalized","slug":"automatic-gradient-descent-with-generalized","title":"Gradient descent with generalized Newton's method","date":"2024-07-03","arxiv_id":"2407.02772","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shiyunxu/autogen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-llm-abilities-in-idiomatic","title":"Improving LLM Abilities in Idiomatic Translation","date":"2024-07-03","arxiv_id":"2407.03518","n_code_links":0,"syntology":null},{"paper":null,"slug":"obfuscatune-obfuscated-offsite-fine-tuning","title":"ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets","date":"2024-07-03","arxiv_id":"2407.02960","n_code_links":0,"syntology":null},{"paper":null,"slug":"ospc-artificial-vlm-features-for-hateful-meme","title":"OSPC: Artificial VLM Features for Hateful Meme Detection","date":"2024-07-03","arxiv_id":"2407.12836","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-code-clone-detection-capability","title":"Assessing the Code Clone Detection Capability of Large Language Models","date":"2024-07-02","arxiv_id":"2407.02402","n_code_links":0,"syntology":null},{"paper":"/paper/gptcast-a-weather-language-model-for","slug":"gptcast-a-weather-language-model-for","title":"GPTCast: a weather language model for precipitation nowcasting","date":"2024-07-02","arxiv_id":"2407.02089","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-dc-link-capacitor-current-ripple","title":"Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits Using Fine-Tuned Large Language Models","date":"2024-07-01","arxiv_id":"2407.01724","n_code_links":0,"syntology":null},{"paper":"/paper/parm-efficient-training-of-large-sparsely","slug":"parm-efficient-training-of-large-sparsely","title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules","date":"2024-06-30","arxiv_id":"2407.00599","n_code_links":1,"syntology":null},{"paper":"/paper/machine-learning-predictors-for-min-entropy","slug":"machine-learning-predictors-for-min-entropy","title":"Machine Learning Predictors for Min-Entropy Estimation","date":"2024-06-28","arxiv_id":"2406.19983","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalebio-scalable-bilevel-optimization-for","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","date":"2024-06-28","arxiv_id":"2406.19976","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuned-network-relies-on-generic","title":"Fine-tuned network relies on generic representation to solve unseen cognitive task","date":"2024-06-27","arxiv_id":"2406.18926","n_code_links":0,"syntology":null},{"paper":null,"slug":"granite-function-calling-model-introducing","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","date":"2024-06-27","arxiv_id":"2407.00121","n_code_links":0,"syntology":null},{"paper":"/paper/factfinders-at-checkthat-2024-refining-check","slug":"factfinders-at-checkthat-2024-refining-check","title":"FactFinders at CheckThat! 2024: Refining Check-worthy Statement Detection with LLMs through Data Pruning","date":"2024-06-26","arxiv_id":"2406.18297","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-entity-recognition-using-ensembles","title":"Improving Entity Recognition Using Ensembles of Deep Learning and Fine-tuned Large Language Models: A Case Study on Adverse Event Extraction from Multiple Sources","date":"2024-06-26","arxiv_id":"2406.18049","n_code_links":0,"syntology":null},{"paper":"/paper/mathodyssey-benchmarking-mathematical-problem","slug":"mathodyssey-benchmarking-mathematical-problem","title":"MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data","date":"2024-06-26","arxiv_id":"2406.18321","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}}],"record_sha256":"0af4e46e7453c1e7ed1c657c47cc40e0a377580b60abcb759e8e324f8fec5dd0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}