{"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/12","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":12,"pages_in_order":20,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/method/discriminative-fine-tuning/papers/13","papers":[{"paper":null,"slug":"discriminative-speech-recognition-rescoring","title":"Discriminative Speech Recognition Rescoring with Pre-trained Language Models","date":"2023-10-10","arxiv_id":"2310.06248","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-as-an-agronomist-assistant-answering","title":"GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models","date":"2023-10-10","arxiv_id":"2310.06225","n_code_links":0,"syntology":null},{"paper":"/paper/humans-and-language-models-diverge-when","slug":"humans-and-language-models-diverge-when","title":"Humans and language models diverge when predicting repeating text","date":"2023-10-10","arxiv_id":"2310.06408","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["huthlab/lm-repeating-text"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"foundation-models-meet-visualizations","title":"Foundation Models Meet Visualizations: Challenges and Opportunities","date":"2023-10-09","arxiv_id":"2310.05771","n_code_links":0,"syntology":null},{"paper":"/paper/distantly-supervised-joint-entity-and","slug":"distantly-supervised-joint-entity-and","title":"Distantly-Supervised Joint Extraction with Noise-Robust Learning","date":"2023-10-08","arxiv_id":"2310.04994","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-self-supervised-speech-and-language-models","title":"Do self-supervised speech and language models extract similar representations as human brain?","date":"2023-10-07","arxiv_id":"2310.04645","n_code_links":0,"syntology":null},{"paper":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"question-focused-summarization-by-decomposing","title":"Question-focused Summarization by Decomposing Articles into Facts and Opinions and Retrieving Entities","date":"2023-10-07","arxiv_id":"2310.04880","n_code_links":0,"syntology":null},{"paper":"/paper/copy-suppression-comprehensively","slug":"copy-suppression-comprehensively","title":"Copy Suppression: Comprehensively Understanding an Attention Head","date":"2023-10-06","arxiv_id":"2310.04625","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["callummcdougall/seri-mats-2023-streamlit-pages"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"keyword-augmented-retrieval-novel-framework","title":"Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface","date":"2023-10-06","arxiv_id":"2310.04205","n_code_links":0,"syntology":null},{"paper":"/paper/smoothllm-defending-large-language-models","slug":"smoothllm-defending-large-language-models","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","date":"2023-10-05","arxiv_id":"2310.03684","n_code_links":1,"syntology":null},{"paper":"/paper/discriminative-training-of-vbx-diarization","slug":"discriminative-training-of-vbx-diarization","title":"Discriminative Training of VBx Diarization","date":"2023-10-04","arxiv_id":"2310.02732","n_code_links":1,"syntology":null},{"paper":"/paper/memoria-hebbian-memory-architecture-for-human","slug":"memoria-hebbian-memory-architecture-for-human","title":"Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture","date":"2023-10-04","arxiv_id":"2310.03052","n_code_links":1,"syntology":{"ran":1,"of":10,"n_ran_checked":0,"n_instrument":1,"unverified":9,"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) · 9 unverified","official":{"repos":["cosmoquester/memoria"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/nola-networks-as-linear-combination-of-low","slug":"nola-networks-as-linear-combination-of-low","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","date":"2023-10-04","arxiv_id":"2310.02556","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["UCDvision/NOLA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"retrieval-meets-long-context-large-language","title":"Retrieval meets Long Context Large Language Models","date":"2023-10-04","arxiv_id":"2310.03025","n_code_links":0,"syntology":null},{"paper":null,"slug":"polysketchformer-fast-transformers-via","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","date":"2023-10-02","arxiv_id":"2310.01655","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-and-mitigating-object-hallucination","slug":"analyzing-and-mitigating-object-hallucination","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","date":"2023-10-01","arxiv_id":"2310.00754","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":2,"n_instrument":5,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yiyangzhou/lure"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rolellm-benchmarking-eliciting-and-enhancing","slug":"rolellm-benchmarking-eliciting-and-enhancing","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","date":"2023-10-01","arxiv_id":"2310.00746","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-evaluation-of-gpt-models-for-phenotype","title":"An evaluation of GPT models for phenotype concept recognition","date":"2023-09-29","arxiv_id":"2309.17169","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-mobile-interaction-enabling-a","title":"Revolutionizing Mobile Interaction: Enabling a 3 Billion Parameter GPT LLM on Mobile","date":"2023-09-29","arxiv_id":"2310.01434","n_code_links":0,"syntology":null},{"paper":null,"slug":"split-and-merge-aligning-position-biases-in","title":"Split and Merge: Aligning Position Biases in LLM-based Evaluators","date":"2023-09-29","arxiv_id":"2310.01432","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-and-inference-of-large-language","title":"Training and inference of large language models using 8-bit floating point","date":"2023-09-29","arxiv_id":"2309.17224","n_code_links":0,"syntology":null},{"paper":null,"slug":"ae-gpt-using-large-language-models-to-extract","title":"AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events","date":"2023-09-28","arxiv_id":"2309.16150","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-soft-ideologization-via","title":"Large Language Model Soft Ideologization via AI-Self-Consciousness","date":"2023-09-28","arxiv_id":"2309.16167","n_code_links":0,"syntology":null},{"paper":"/paper/mindgpt-interpreting-what-you-see-with-non","slug":"mindgpt-interpreting-what-you-see-with-non","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","date":"2023-09-27","arxiv_id":"2309.15729","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"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) · 4 unverified","official":{"repos":["jxuanc/mindgpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"comparative-analysis-of-artificial","title":"Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models","date":"2023-09-26","arxiv_id":"2309.14735","n_code_links":0,"syntology":null},{"paper":"/paper/loggpt-log-anomaly-detection-via-gpt","slug":"loggpt-log-anomaly-detection-via-gpt","title":"LogGPT: Log Anomaly Detection via GPT","date":"2023-09-25","arxiv_id":"2309.14482","n_code_links":1,"syntology":null},{"paper":"/paper/seeing-is-not-always-believing-invisible","slug":"seeing-is-not-always-believing-invisible","title":"Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models","date":"2023-09-24","arxiv_id":"2309.13579","n_code_links":1,"syntology":null},{"paper":"/paper/amplify-attention-based-mixup-for-performance","slug":"amplify-attention-based-mixup-for-performance","title":"AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer","date":"2023-09-22","arxiv_id":"2309.12689","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-and-control-mechanisms","slug":"large-language-models-and-control-mechanisms","title":"Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts","date":"2023-09-22","arxiv_id":"2309.13202","n_code_links":1,"syntology":null},{"paper":"/paper/bad-actor-good-advisor-exploring-the-role-of","slug":"bad-actor-good-advisor-exploring-the-role-of","title":"Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection","date":"2023-09-21","arxiv_id":"2309.12247","n_code_links":1,"syntology":null},{"paper":null,"slug":"constraints-first-a-new-mdd-based-model-to","title":"Constraints First: A New MDD-based Model to Generate Sentences Under Constraints","date":"2023-09-21","arxiv_id":"2309.12415","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-spanish-pre-trained","slug":"sequence-to-sequence-spanish-pre-trained","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","date":"2023-09-20","arxiv_id":"2309.11259","n_code_links":1,"syntology":null},{"paper":"/paper/the-languini-kitchen-enabling-language","slug":"the-languini-kitchen-enabling-language","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","date":"2023-09-20","arxiv_id":"2309.11197","n_code_links":1,"syntology":null},{"paper":null,"slug":"rigorously-assessing-natural-language","title":"Rigorously Assessing Natural Language Explanations of Neurons","date":"2023-09-19","arxiv_id":"2309.10312","n_code_links":0,"syntology":null},{"paper":"/paper/recap-retrieval-augmented-audio-captioning","slug":"recap-retrieval-augmented-audio-captioning","title":"RECAP: Retrieval-Augmented Audio Captioning","date":"2023-09-18","arxiv_id":"2309.09836","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sreyan88/recap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-ontology-construction-with-language","title":"Towards Ontology Construction with Language Models","date":"2023-09-18","arxiv_id":"2309.09898","n_code_links":0,"syntology":null},{"paper":"/paper/a-modern-turkish-poet-fine-tuned-gpt-2","slug":"a-modern-turkish-poet-fine-tuned-gpt-2","title":"A Modern Turkish Poet: Fine-Tuned GPT-2","date":"2023-09-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/casteist-but-not-racist-quantifying","slug":"casteist-but-not-racist-quantifying","title":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","date":"2023-09-15","arxiv_id":"2309.08573","n_code_links":1,"syntology":null},{"paper":"/paper/cure-the-headache-of-transformers-via","slug":"cure-the-headache-of-transformers-via","title":"CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending","date":"2023-09-15","arxiv_id":"2309.08646","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-lab-next-generation-of-optimal-chemistry","title":"GPT-Lab: Next Generation Of Optimal Chemistry Discovery By GPT Driven Robotic Lab","date":"2023-09-15","arxiv_id":"2309.16721","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-nature-of-large-language-models","title":"Assessing the nature of large language models: A caution against anthropocentrism","date":"2023-09-14","arxiv_id":"2309.07683","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-mt-competitive-for-high-but-not-low","slug":"chatgpt-mt-competitive-for-high-but-not-low","title":"ChatGPT MT: Competitive for High- (but not Low-) Resource Languages","date":"2023-09-14","arxiv_id":"2309.07423","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["cmu-llab/gpt_mt_benchmark"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/traveling-words-a-geometric-interpretation-of","slug":"traveling-words-a-geometric-interpretation-of","title":"Traveling Words: A Geometric Interpretation of Transformers","date":"2023-09-13","arxiv_id":"2309.07315","n_code_links":1,"syntology":null},{"paper":"/paper/2309-05973","slug":"2309-05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","date":"2023-09-12","arxiv_id":"2309.05973","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":12,"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":{"repos":["xanderdavies/circuit-breaking"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2309-06112","title":"Characterizing Latent Perspectives of Media Houses Towards Public Figures","date":"2023-09-12","arxiv_id":"2309.06112","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-large-language-models-for-ontology","slug":"exploring-large-language-models-for-ontology","title":"Exploring Large Language Models for Ontology Alignment","date":"2023-09-12","arxiv_id":"2309.07172","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-the-potential-of-large-language","title":"Unveiling the potential of large language models in generating semantic and cross-language clones","date":"2023-09-12","arxiv_id":"2309.06424","n_code_links":0,"syntology":null},{"paper":"/paper/memory-injections-correcting-multi-hop","slug":"memory-injections-correcting-multi-hop","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","date":"2023-09-11","arxiv_id":"2309.05605","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["msakarvadia/memory_injections"],"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":"zero-shot-learning-with-minimum-instruction","title":"Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model","date":"2023-09-11","arxiv_id":"2309.05475","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","n_code_links":2,"syntology":null},{"paper":"/paper/zero-shot-audio-captioning-via-audibility","slug":"zero-shot-audio-captioning-via-audibility","title":"Zero-Shot Audio Captioning via Audibility Guidance","date":"2023-09-07","arxiv_id":"2309.03884","n_code_links":0,"syntology":null},{"paper":"/paper/codeapex-a-bilingual-programming-evaluation","slug":"codeapex-a-bilingual-programming-evaluation","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","date":"2023-09-05","arxiv_id":"2309.01940","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-you-trust-chatgpt-perceived-credibility-of","title":"Do You Trust ChatGPT? -- Perceived Credibility of Human and AI-Generated Content","date":"2023-09-05","arxiv_id":"2309.02524","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-androids-dream-of-fictional-references-a","title":"Do androids dream of fictional references? A bibliographic dialogue with ChatGPT3.5","date":"2023-09-04","arxiv_id":"2312.00789","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-semantic-monitoring","title":"Large Language Models for Semantic Monitoring of Corporate Disclosures: A Case Study on Korea's Top 50 KOSPI Companies","date":"2023-09-01","arxiv_id":"2309.00208","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-do-universal-adversarial-attacks-work-on","title":"Why do universal adversarial attacks work on large language models?: Geometry might be the answer","date":"2023-09-01","arxiv_id":"2309.00254","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-has-become-financially-literate-insights","title":"GPT has become financially literate: Insights from financial literacy tests of GPT and a preliminary test of how people use it as a source of advice","date":"2023-08-31","arxiv_id":"2309.00649","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-data-preprocessors","title":"Large Language Models as Data Preprocessors","date":"2023-08-30","arxiv_id":"2308.16361","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-uncertainty-in-answers-from-any","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","date":"2023-08-30","arxiv_id":"2308.16175","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-bank-with-chatgpt-few-shot-text","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","date":"2023-08-28","arxiv_id":"2308.14634","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-independent-xla-optimization-using","title":"Target-independent XLA optimization using Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14364","n_code_links":0,"syntology":null},{"paper":"/paper/textrolspeech-a-text-style-control-speech","slug":"textrolspeech-a-text-style-control-speech","title":"TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models","date":"2023-08-28","arxiv_id":"2308.14430","n_code_links":1,"syntology":null},{"paper":"/paper/examining-user-friendly-and-open-sourced","slug":"examining-user-friendly-and-open-sourced","title":"Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models","date":"2023-08-27","arxiv_id":"2308.14149","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-knowledge-distillation-for-bert","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","date":"2023-08-26","arxiv_id":"2308.13958","n_code_links":0,"syntology":null},{"paper":"/paper/mllm-dataengine-an-iterative-refinement","slug":"mllm-dataengine-an-iterative-refinement","title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM","date":"2023-08-25","arxiv_id":"2308.13566","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opendatalab/mllm-dataengine"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transforming-the-output-of-generative-pre","title":"Transforming the Output of Generative Pre-trained Transformer: The Influence of the PGI Framework on Attention Dynamics","date":"2023-08-25","arxiv_id":"2308.13317","n_code_links":0,"syntology":null},{"paper":null,"slug":"financial-news-analytics-using-fine-tuned","title":"Financial News Analytics Using Fine-Tuned Llama 2 GPT Model","date":"2023-08-24","arxiv_id":"2308.13032","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-on-graphs","slug":"evaluating-large-language-models-on-graphs","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","date":"2023-08-22","arxiv_id":"2308.11224","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ayame1006/llmtograph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-effectiveness-of-gpt-models-in","title":"Exploring the Effectiveness of GPT Models in Test-Taking: A Case Study of the Driver's License Knowledge Test","date":"2023-08-22","arxiv_id":"2308.11827","n_code_links":0,"syntology":null},{"paper":"/paper/mulmarker-a-gpt-assisted-comprehensive","slug":"mulmarker-a-gpt-assisted-comprehensive","title":"MulMarker: a comprehensive framework for identifying multi-gene prognostic signatures","date":"2023-08-22","arxiv_id":"2308.11349","n_code_links":1,"syntology":null},{"paper":null,"slug":"tryage-real-time-intelligent-routing-of-user","title":"Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models","date":"2023-08-22","arxiv_id":"2308.11601","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-in-the-loop-adaptive-decision-making-for","title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","date":"2023-08-21","arxiv_id":"2308.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradientcoin-a-peer-to-peer-decentralized","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","date":"2023-08-21","arxiv_id":"2308.10502","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-on-wikipedia-style","slug":"large-language-models-on-wikipedia-style","title":"Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts","date":"2023-08-21","arxiv_id":"2308.10410","n_code_links":1,"syntology":null},{"paper":"/paper/activation-addition-steering-language-models","slug":"activation-addition-steering-language-models","title":"Steering Language Models With Activation Engineering","date":"2023-08-20","arxiv_id":"2308.10248","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["montemac/activation_additions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-good-are-large-language-models-at-out-of","slug":"how-good-are-large-language-models-at-out-of","title":"How Good Are LLMs at Out-of-Distribution Detection?","date":"2023-08-20","arxiv_id":"2308.10261","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["awenbocc/llm-ood"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/data-to-text-generation-for-severely-under","slug":"data-to-text-generation-for-severely-under","title":"Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate","date":"2023-08-19","arxiv_id":"2308.09957","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-tailored-handwritten-text-recognition","title":"A tailored Handwritten-Text-Recognition System for Medieval Latin","date":"2023-08-18","arxiv_id":"2308.09368","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-preliminary-study-on-a-conceptual-game","title":"A Preliminary Study on a Conceptual Game Feature Generation and Recommendation System","date":"2023-08-16","arxiv_id":"2308.13538","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximating-human-like-few-shot-learning","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","date":"2023-08-14","arxiv_id":"2308.06942","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-individual-trajectories-using-gpt","title":"Generating Individual Trajectories Using GPT-2 Trained from Scratch on Encoded Spatiotemporal Data","date":"2023-08-14","arxiv_id":"2308.07940","n_code_links":0,"syntology":null},{"paper":"/paper/llm-self-defense-by-self-examination-llms","slug":"llm-self-defense-by-self-examination-llms","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","date":"2023-08-14","arxiv_id":"2308.07308","n_code_links":1,"syntology":null},{"paper":null,"slug":"playing-with-words-comparing-the-vocabulary","title":"Playing with Words: Comparing the Vocabulary and Lexical Richness of ChatGPT and Humans","date":"2023-08-14","arxiv_id":"2308.07462","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-similarity-loss-for-neural-source","slug":"semantic-similarity-loss-for-neural-source","title":"Semantic Similarity Loss for Neural Source Code Summarization","date":"2023-08-14","arxiv_id":"2308.07429","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-phenotype-recognition-in-clinical","slug":"enhancing-phenotype-recognition-in-clinical","title":"Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT","date":"2023-08-11","arxiv_id":"2308.06294","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-to-identify-social","slug":"large-language-models-to-identify-social","title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records","date":"2023-08-11","arxiv_id":"2308.06354","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["aim-harvard/sdoh"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","n_code_links":2,"syntology":{"ran":16,"of":27,"n_ran_checked":16,"n_instrument":0,"unverified":11,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"testing-gpt-4-with-wolfram-alpha-and-code","title":"Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems","date":"2023-08-10","arxiv_id":"2308.05713","n_code_links":0,"syntology":null},{"paper":"/paper/weaverbird-empowering-financial-decision","slug":"weaverbird-empowering-financial-decision","title":"WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine","date":"2023-08-10","arxiv_id":"2308.05361","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-on-using-large-language-1","title":"An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures","date":"2023-08-09","arxiv_id":"2308.04898","n_code_links":0,"syntology":null},{"paper":"/paper/llmebench-a-flexible-framework-for","slug":"llmebench-a-flexible-framework-for","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","date":"2023-08-09","arxiv_id":"2308.04945","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-color-similarity-structures-between","title":"Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models","date":"2023-08-08","arxiv_id":"2308.04381","n_code_links":0,"syntology":null},{"paper":null,"slug":"i-was-a-data-augmentation-method-with-gpt-2","title":"I-WAS: a Data Augmentation Method with GPT-2 for Simile Detection","date":"2023-08-08","arxiv_id":"2308.04109","n_code_links":0,"syntology":null},{"paper":null,"slug":"establishing-trust-in-chatgpt-biomedical","title":"Fact-Checking Generative AI: Ontology-Driven Biological Graphs for Disease-Gene Link Verification","date":"2023-08-07","arxiv_id":"2308.03929","n_code_links":0,"syntology":null},{"paper":"/paper/when-gpt-meets-program-analysis-towards","slug":"when-gpt-meets-program-analysis-towards","title":"GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis","date":"2023-08-07","arxiv_id":"2308.03314","n_code_links":1,"syntology":null},{"paper":"/paper/explaining-relation-classification-models","slug":"explaining-relation-classification-models","title":"Explaining Relation Classification Models with Semantic Extents","date":"2023-08-04","arxiv_id":"2308.02193","n_code_links":2,"syntology":null},{"paper":"/paper/towards-personalized-prompt-model-retrieval","slug":"towards-personalized-prompt-model-retrieval","title":"GEMRec: Towards Generative Model Recommendation","date":"2023-08-04","arxiv_id":"2308.02205","n_code_links":1,"syntology":null},{"paper":"/paper/baby-llama-knowledge-distillation-from-an","slug":"baby-llama-knowledge-distillation-from-an","title":"Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty","date":"2023-08-03","arxiv_id":"2308.02019","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-correction-remain-an-problem-for-large","title":"Does Correction Remain A Problem For Large Language Models?","date":"2023-08-03","arxiv_id":"2308.01776","n_code_links":0,"syntology":null}],"record_sha256":"2c25a0e77d0713decdff2f2b881caaa974172800ec5d387bbc74f7010d821d2a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}