{"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/5","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":5,"pages_in_order":20,"rows_per_page":100,"rows":[401,500],"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/4","next":"/method/discriminative-fine-tuning/papers/6","papers":[{"paper":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-the-chaos-enhancing-jailbreak","slug":"deciphering-the-chaos-enhancing-jailbreak","title":"Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation","date":"2024-10-15","arxiv_id":"2410.11317","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["qizhangli/adversarial-prompt-translator"],"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":"evidence-of-cognitive-deficits","title":"Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis","date":"2024-10-15","arxiv_id":"2410.11756","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-hate-lost-in-translation-evaluation-of","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","date":"2024-10-15","arxiv_id":"2410.11230","n_code_links":0,"syntology":null},{"paper":"/paper/mtu-bench-a-multi-granularity-tool-use","slug":"mtu-bench-a-multi-granularity-tool-use","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11710","n_code_links":1,"syntology":null},{"paper":null,"slug":"nonlinear-gaussian-process-tomography-with","title":"Nonlinear Gaussian process tomography with imposed non-negativity constraints on physical quantities for plasma diagnostics","date":"2024-10-15","arxiv_id":"2410.11454","n_code_links":0,"syntology":null},{"paper":"/paper/double-jeopardy-and-climate-impact-in-the-use","slug":"double-jeopardy-and-climate-impact-in-the-use","title":"Double Jeopardy and Climate Impact in the Use of Large Language Models: Socio-economic Disparities and Reduced Utility for Non-English Speakers","date":"2024-10-14","arxiv_id":"2410.10665","n_code_links":1,"syntology":null},{"paper":"/paper/one-language-many-gaps-evaluating-dialect","slug":"one-language-many-gaps-evaluating-dialect","title":"One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","date":"2024-10-14","arxiv_id":"2410.11005","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fangru-lin/redial_dialect_robustness_fairness"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"performance-in-a-dialectal-profiling-task-of","title":"Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese","date":"2024-10-14","arxiv_id":"2410.10991","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-multi-head-attention-via","slug":"towards-better-multi-head-attention-via","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","date":"2024-10-14","arxiv_id":"2410.10914","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"phrase":"4 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dashenzi721/csp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-in-context-learning-really-generalize-to","title":"Can In-context Learning Really Generalize to Out-of-distribution Tasks?","date":"2024-10-13","arxiv_id":"2410.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-of-llms-in-making","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","date":"2024-10-13","arxiv_id":"2410.09992","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-implicit-bias-in-large-language","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","date":"2024-10-13","arxiv_id":"2410.12864","n_code_links":0,"syntology":null},{"paper":null,"slug":"m2m-gen-a-multimodal-framework-for-automated","title":"M2M-Gen: A Multimodal Framework for Automated Background Music Generation in Japanese Manga Using Large Language Models","date":"2024-10-13","arxiv_id":"2410.09928","n_code_links":0,"syntology":null},{"paper":null,"slug":"llinstruct-an-instruction-tuned-model-for","title":"\\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments","date":"2024-10-12","arxiv_id":"2410.09314","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-in-house-large-language-models-to","title":"Fine-Tuning In-House Large Language Models to Infer Differential Diagnosis from Radiology Reports","date":"2024-10-11","arxiv_id":"2410.09234","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanity-in-ai-detecting-the-personality-of","title":"Humanity in AI: Detecting the Personality of Large Language Models","date":"2024-10-11","arxiv_id":"2410.08545","n_code_links":0,"syntology":null},{"paper":"/paper/synth-sonar-sonar-image-synthesis-with","slug":"synth-sonar-sonar-image-synthesis-with","title":"Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting","date":"2024-10-11","arxiv_id":"2410.08612","n_code_links":1,"syntology":null},{"paper":"/paper/adam-exploits-ell-infty-geometry-of-loss","slug":"adam-exploits-ell-infty-geometry-of-loss","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","date":"2024-10-10","arxiv_id":"2410.08198","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"7 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mohamad-amin/adam-coordinate-adaptivity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"capturing-bias-diversity-in-llms","title":"Capturing Bias Diversity in LLMs","date":"2024-10-09","arxiv_id":"2410.12839","n_code_links":0,"syntology":null},{"paper":null,"slug":"sage-scalable-ground-truth-evaluations-for","title":"SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders","date":"2024-10-09","arxiv_id":"2410.07456","n_code_links":0,"syntology":null},{"paper":"/paper/a-second-order-like-optimizer-with-adaptive","slug":"a-second-order-like-optimizer-with-adaptive","title":"A second-order-like optimizer with adaptive gradient scaling for deep learning","date":"2024-10-08","arxiv_id":"2410.05871","n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-evolve-enhancing-large-language-model-s","title":"Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning Framework","date":"2024-10-08","arxiv_id":"2410.06328","n_code_links":0,"syntology":null},{"paper":"/paper/coevolving-with-the-other-you-fine-tuning-llm","slug":"coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","arxiv_id":"2410.06101","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Harry67Hu/CORY"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-free-energy-in-pretraining-model","title":"Leveraging free energy in pretraining model selection for improved fine-tuning","date":"2024-10-08","arxiv_id":"2410.05612","n_code_links":0,"syntology":null},{"paper":null,"slug":"anyattack-towards-large-scale-self-supervised","title":"AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models","date":"2024-10-07","arxiv_id":"2410.05346","n_code_links":0,"syntology":null},{"paper":null,"slug":"lpzero-language-model-zero-cost-proxy-search","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","date":"2024-10-07","arxiv_id":"2410.04808","n_code_links":0,"syntology":null},{"paper":"/paper/famma-a-benchmark-for-financial-domain","slug":"famma-a-benchmark-for-financial-domain","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","date":"2024-10-06","arxiv_id":"2410.04526","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["famma-bench/bench-script"],"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/large-language-model-inference-acceleration-a","slug":"large-language-model-inference-acceleration-a","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","date":"2024-10-06","arxiv_id":"2410.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"protocollm-automatic-evaluation-framework-of","title":"ProtocoLLM: Automatic Evaluation Framework of LLMs on Domain-Specific Scientific Protocol Formulation Tasks","date":"2024-10-06","arxiv_id":"2410.04601","n_code_links":0,"syntology":null},{"paper":"/paper/gamified-crowd-sourcing-of-high-quality-data","slug":"gamified-crowd-sourcing-of-high-quality-data","title":"Gamified crowd-sourcing of high-quality data for visual fine-tuning","date":"2024-10-05","arxiv_id":"2410.04038","n_code_links":0,"syntology":null},{"paper":"/paper/how-language-models-prioritize-contextual","slug":"how-language-models-prioritize-contextual","title":"How Language Models Prioritize Contextual Grammatical Cues?","date":"2024-10-04","arxiv_id":"2410.03447","n_code_links":1,"syntology":null},{"paper":"/paper/steering-large-language-models-between-code","slug":"steering-large-language-models-between-code","title":"Steering Large Language Models between Code Execution and Textual Reasoning","date":"2024-10-04","arxiv_id":"2410.03524","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-prompts-to-guide-large-language-models","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","date":"2024-10-04","arxiv_id":"2410.03848","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphaintegrator-transformer-action-search-for","title":"AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs","date":"2024-10-03","arxiv_id":"2410.02666","n_code_links":0,"syntology":null},{"paper":null,"slug":"llava-critic-learning-to-evaluate-multimodal","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02712","n_code_links":0,"syntology":null},{"paper":null,"slug":"plots-unlock-time-series-understanding-in","title":"Plots Unlock Time-Series Understanding in Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02637","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-deductive-coding-in-discourse","slug":"automatic-deductive-coding-in-discourse","title":"Automatic deductive coding in discourse analysis: an application of large language models in learning analytics","date":"2024-10-02","arxiv_id":"2410.01240","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-llm-fine-tuning-for-text-to-sqls-by","title":"Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement","date":"2024-10-02","arxiv_id":"2410.01869","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-adaptation-of-unlimiformer-for-decoder","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","date":"2024-10-02","arxiv_id":"2410.01637","n_code_links":0,"syntology":null},{"paper":"/paper/quantifying-generalization-complexity-for","slug":"quantifying-generalization-complexity-for","title":"Quantifying Generalization Complexity for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01769","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhentingqi/scylla"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/seeing-eye-to-ai-human-alignment-via-gaze","slug":"seeing-eye-to-ai-human-alignment-via-gaze","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01532","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["telefonica-scientific-research/gaze_reward"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparse-attention-decomposition-applied-to","slug":"sparse-attention-decomposition-applied-to","title":"Sparse Attention Decomposition Applied to Circuit Tracing","date":"2024-10-01","arxiv_id":"2410.00340","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-fairness-of-task-adaptive","slug":"evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","n_code_links":1,"syntology":null},{"paper":null,"slug":"modelando-procesos-cognitivos-de-la-lectura","title":"Modelando procesos cognitivos de la lectura natural con GPT-2","date":"2024-09-30","arxiv_id":"2409.20174","n_code_links":0,"syntology":null},{"paper":"/paper/analog-in-memory-computing-attention","slug":"analog-in-memory-computing-attention","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","date":"2024-09-28","arxiv_id":"2409.19315","n_code_links":1,"syntology":null},{"paper":"/paper/cottention-linear-transformers-with-cosine","slug":"cottention-linear-transformers-with-cosine","title":"Cottention: Linear Transformers With Cosine Attention","date":"2024-09-27","arxiv_id":"2409.18747","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["gmongaras/Cottention_Transformer"],"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":"experimental-evaluation-of-machine-learning","title":"Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture","date":"2024-09-27","arxiv_id":"2409.18568","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-unidirectional-bidirectional-and","title":"Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code","date":"2024-09-26","arxiv_id":"2409.17513","n_code_links":0,"syntology":null},{"paper":null,"slug":"t3-a-novel-zero-shot-transfer-learning","title":"T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task","date":"2024-09-26","arxiv_id":"2409.17640","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-application-of-gpt-4-in-grading-design","title":"The application of GPT-4 in grading design university students' assignment and providing feedback: An exploratory study","date":"2024-09-26","arxiv_id":"2409.17698","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-and-machine-learning-advancing","title":"Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Handy Appetizer","date":"2024-09-25","arxiv_id":"2409.17120","n_code_links":0,"syntology":null},{"paper":null,"slug":"severity-prediction-in-mental-health-llm","title":"Severity Prediction in Mental Health: LLM-based Creation, Analysis, Evaluation of a Novel Multilingual Dataset","date":"2024-09-25","arxiv_id":"2409.17397","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-for-sparse-multidimensional","slug":"data-augmentation-for-sparse-multidimensional","title":"Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AI","date":"2024-09-24","arxiv_id":"2409.15631","n_code_links":1,"syntology":null},{"paper":"/paper/self-attention-as-an-attractor-network","slug":"self-attention-as-an-attractor-network","title":"Self-attention as an attractor network: transient memories without backpropagation","date":"2024-09-24","arxiv_id":"2409.16112","n_code_links":1,"syntology":null},{"paper":null,"slug":"advancing-depression-detection-on-social","title":"Advancing Depression Detection on Social Media Platforms Through Fine-Tuned Large Language Models","date":"2024-09-23","arxiv_id":"2409.14794","n_code_links":0,"syntology":null},{"paper":null,"slug":"chattronics-using-gpts-to-assist-in-the","title":"Chattronics: using GPTs to assist in the design of data acquisition systems","date":"2024-09-23","arxiv_id":"2409.15183","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-policy-analysis-through-prompt","title":"Privacy Policy Analysis through Prompt Engineering for LLMs","date":"2024-09-23","arxiv_id":"2409.14879","n_code_links":0,"syntology":null},{"paper":null,"slug":"safe-guard-an-llm-agent-for-real-time-voice","title":"Safe Guard: an LLM-agent for Real-time Voice-based Hate Speech Detection in Social Virtual Reality","date":"2024-09-23","arxiv_id":"2409.15623","n_code_links":0,"syntology":null},{"paper":"/paper/sdba-a-stealthy-and-long-lasting-durable","slug":"sdba-a-stealthy-and-long-lasting-durable","title":"SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning","date":"2024-09-23","arxiv_id":"2409.14805","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-are-one-shot-url-classifiers-and","title":"LLMs are One-Shot URL Classifiers and Explainers","date":"2024-09-22","arxiv_id":"2409.14306","n_code_links":0,"syntology":null},{"paper":"/paper/2409-14037","slug":"2409-14037","title":"Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators","date":"2024-09-21","arxiv_id":"2409.14037","n_code_links":1,"syntology":null},{"paper":null,"slug":"drift-to-remember","title":"Drift to Remember","date":"2024-09-21","arxiv_id":"2409.13997","n_code_links":0,"syntology":null},{"paper":"/paper/loop-residual-neural-networks-for-iterative","slug":"loop-residual-neural-networks-for-iterative","title":"Loop Neural Networks for Parameter Sharing","date":"2024-09-21","arxiv_id":"2409.14199","n_code_links":0,"syntology":null},{"paper":null,"slug":"emmett-efficient-multimodal-machine","title":"EMMeTT: Efficient Multimodal Machine Translation Training","date":"2024-09-20","arxiv_id":"2409.13523","n_code_links":0,"syntology":null},{"paper":"/paper/fair-gpt-a-virtual-consultant-for-research","slug":"fair-gpt-a-virtual-consultant-for-research","title":"FAIR GPT: A virtual consultant for research data management in ChatGPT","date":"2024-09-20","arxiv_id":"2410.07108","n_code_links":1,"syntology":null},{"paper":null,"slug":"hut-a-more-computation-efficient-fine-tuning","title":"HUT: A More Computation Efficient Fine-Tuning Method With Hadamard Updated Transformation","date":"2024-09-20","arxiv_id":"2409.13501","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-knowledge-graphs-and-llms-to","title":"Leveraging Knowledge Graphs and LLMs to Support and Monitor Legislative Systems","date":"2024-09-20","arxiv_id":"2409.13252","n_code_links":0,"syntology":null},{"paper":null,"slug":"talkmosaic-interactive-photomosaic-with-multi","title":"TalkMosaic: Interactive PhotoMosaic with Multi-modal LLM Q&A Interactions","date":"2024-09-20","arxiv_id":"2409.13941","n_code_links":0,"syntology":null},{"paper":null,"slug":"recommendation-with-generative-models","title":"Recommendation with Generative Models","date":"2024-09-18","arxiv_id":"2409.15173","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-framework-to-classify-business","title":"A Unified Framework to Classify Business Activities into International Standard Industrial Classification through Large Language Models for Circular Economy","date":"2024-09-17","arxiv_id":"2409.18988","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimenting-with-legal-ai-solutions-the","title":"Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice","date":"2024-09-12","arxiv_id":"2409.07713","n_code_links":0,"syntology":null},{"paper":null,"slug":"stable-language-model-pre-training-by","title":"Stable Language Model Pre-training by Reducing Embedding Variability","date":"2024-09-12","arxiv_id":"2409.07787","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-mathematical-framework-for-objective","title":"A Novel Mathematical Framework for Objective Characterization of Ideas","date":"2024-09-11","arxiv_id":"2409.07578","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-fairer-health-recommendations-finding","title":"Towards Fairer Health Recommendations: finding informative unbiased samples via Word Sense Disambiguation","date":"2024-09-11","arxiv_id":"2409.07424","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-large-language-model-pretraining","title":"Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review","date":"2024-09-10","arxiv_id":"2409.06131","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-for-requirements-engineering-a","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","date":"2024-09-10","arxiv_id":"2409.06741","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-sparql-capabilities-of-large","slug":"assessing-sparql-capabilities-of-large","title":"Assessing SPARQL capabilities of Large Language Models","date":"2024-09-09","arxiv_id":"2409.05925","n_code_links":2,"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":"column-vocabulary-association-cva-semantic","title":"Column Vocabulary Association (CVA): semantic interpretation of dataless tables","date":"2024-09-06","arxiv_id":"2409.13709","n_code_links":0,"syntology":null},{"paper":null,"slug":"bypassing-darcy-defense-indistinguishable","title":"Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers","date":"2024-09-05","arxiv_id":"2409.03183","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-open-source-sparse-autoencoders-on","slug":"evaluating-open-source-sparse-autoencoders-on","title":"Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small","date":"2024-09-05","arxiv_id":"2409.04478","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["maheepchaudhary/sae-ravel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sketch-a-toolkit-for-streamlining-llm","title":"Sketch: A Toolkit for Streamlining LLM Operations","date":"2024-09-05","arxiv_id":"2409.03346","n_code_links":0,"syntology":null},{"paper":null,"slug":"dialogue-you-can-trust-human-and-ai","title":"Dialogue You Can Trust: Human and AI Perspectives on Generated Conversations","date":"2024-09-03","arxiv_id":"2409.01808","n_code_links":0,"syntology":null},{"paper":"/paper/it-is-time-to-develop-an-auditing-framework","slug":"it-is-time-to-develop-an-auditing-framework","title":"It is Time to Develop an Auditing Framework to Promote Value Aware Chatbots","date":"2024-09-03","arxiv_id":"2409.01539","n_code_links":1,"syntology":null},{"paper":"/paper/lifegpt-topology-agnostic-generative","slug":"lifegpt-topology-agnostic-generative","title":"LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata","date":"2024-09-03","arxiv_id":"2409.12182","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-era-of-foundation-models-in-medical","title":"The Era of Foundation Models in Medical Imaging is Approaching : A Scoping Review of the Clinical Value of Large-Scale Generative AI Applications in Radiology","date":"2024-09-03","arxiv_id":"2409.12973","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":"/paper/assessing-generative-language-models-in","slug":"assessing-generative-language-models-in","title":"Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain","date":"2024-08-30","arxiv_id":"2408.17362","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-address-open-target","title":"Can Large Language Models Address Open-Target Stance Detection?","date":"2024-08-30","arxiv_id":"2409.00222","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-natural-language","title":"Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering","date":"2024-08-30","arxiv_id":"2408.17006","n_code_links":0,"syntology":null},{"paper":"/paper/training-ultra-long-context-language-model","slug":"training-ultra-long-context-language-model","title":"Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer","date":"2024-08-30","arxiv_id":"2408.16978","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-large-language-models-for-online","title":"Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge","date":"2024-08-29","arxiv_id":"2408.16749","n_code_links":0,"syntology":null},{"paper":"/paper/llava-chef-a-multi-modal-generative-model-for","slug":"llava-chef-a-multi-modal-generative-model-for","title":"LLaVA-Chef: A Multi-modal Generative Model for Food Recipes","date":"2024-08-29","arxiv_id":"2408.16889","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":"a-survey-of-large-language-models-for-3","title":"A Survey of Large Language Models for European Languages","date":"2024-08-27","arxiv_id":"2408.15040","n_code_links":0,"syntology":null},{"paper":"/paper/chartom-a-visual-theory-of-mind-benchmark-for","slug":"chartom-a-visual-theory-of-mind-benchmark-for","title":"CHARTOM: A Visual Theory-of-Mind Benchmark for Multimodal Large Language Models","date":"2024-08-26","arxiv_id":"2408.14419","n_code_links":1,"syntology":null},{"paper":null,"slug":"bidirectional-awareness-induction-in","title":"Bidirectional Awareness Induction in Autoregressive Seq2Seq Models","date":"2024-08-25","arxiv_id":"2408.13959","n_code_links":0,"syntology":null},{"paper":"/paper/vision-language-and-large-language-model","slug":"vision-language-and-large-language-model","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","date":"2024-08-25","arxiv_id":"2409.00084","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-exposure-from-llm-apps-an-in-depth","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","date":"2024-08-23","arxiv_id":"2408.13247","n_code_links":0,"syntology":null}],"record_sha256":"9b6de333cb1d85d38784021d61be99219f2c560f2c88a186e7030227f505a214","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}