{"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/llama/papers/2","list_of":"/method/llama","method":"LLaMA","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":2,"pages_in_order":11,"rows_per_page":100,"rows":[101,200],"of":1062,"counts":{"archive_papers_tagged":1062,"with_a_code_link":423,"where_syntology_ran_a_sample":143,"not_listed_spam_title":0,"listed":1062,"listed_where_code_ran":143,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":127,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":127,"listed_every_run_a_failure_of_syntologys_instrument":16,"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/llama","prev":"/method/llama","next":"/method/llama/papers/3","papers":[{"paper":null,"slug":"analysing-safety-risks-in-llms-fine-tuned","title":"Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data","date":"2025-05-15","arxiv_id":"2505.09974","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-act-multi-step-planning-and-reasoning","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","date":"2025-05-15","arxiv_id":"2505.09970","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-10588","title":"Understanding Gen Alpha Digital Language: Evaluation of LLM Safety Systems for Content Moderation","date":"2025-05-14","arxiv_id":"2505.10588","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-analysis-of-large-language","title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","date":"2025-05-14","arxiv_id":"2505.09056","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-phenotyping-of-pediatric-sepsis","title":"Contextual Phenotyping of Pediatric Sepsis Cohort Using Large Language Models","date":"2025-05-14","arxiv_id":"2505.09805","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-llm-metrics-through-real-world","title":"Evaluating LLM Metrics Through Real-World Capabilities","date":"2025-05-13","arxiv_id":"2505.08253","n_code_links":0,"syntology":null},{"paper":null,"slug":"circuit-partitioning-using-large-language","title":"Circuit Partitioning Using Large Language Models for Quantum Compilation and Simulations","date":"2025-05-12","arxiv_id":"2505.07711","n_code_links":0,"syntology":null},{"paper":null,"slug":"enfoque-odychess-un-metodo-dialectico","title":"Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas","date":"2025-05-10","arxiv_id":"2505.06652","n_code_links":0,"syntology":null},{"paper":null,"slug":"refine-af-a-task-agnostic-framework-to-align","title":"REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback","date":"2025-05-10","arxiv_id":"2505.06548","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-prompting-llms-unlock-hate-speech","title":"Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study","date":"2025-05-09","arxiv_id":"2505.06149","n_code_links":0,"syntology":null},{"paper":null,"slug":"free-and-fair-hardware-a-pathway-to-copyright","title":"Free and Fair Hardware: A Pathway to Copyright Infringement-Free Verilog Generation using LLMs","date":"2025-05-09","arxiv_id":"2505.06096","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-integrated-knowledge-transfer-to","slug":"multimodal-integrated-knowledge-transfer-to","title":"Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications","date":"2025-05-09","arxiv_id":"2505.05736","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-is-next-for-llms-next-generation-ai","title":"What Is Next for LLMs? Next-Generation AI Computing Hardware Using Photonic Chips","date":"2025-05-09","arxiv_id":"2505.05794","n_code_links":0,"syntology":null},{"paper":null,"slug":"lost-in-ocr-translation-vision-based","title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","date":"2025-05-08","arxiv_id":"2505.05666","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-llm-math-reasoning-acceleration-with","title":"Scalable LLM Math Reasoning Acceleration with Low-rank Distillation","date":"2025-05-08","arxiv_id":"2505.07861","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-aloe-family-recipe-for-open-and","title":"The Aloe Family Recipe for Open and Specialized Healthcare LLMs","date":"2025-05-07","arxiv_id":"2505.04388","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-clinical-decision-support-system","title":"Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation","date":"2025-05-06","arxiv_id":"2505.03406","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-the-model-key-differentiators-in-large","title":"Beyond the model: Key differentiators in large language models and multi-agent services","date":"2025-05-05","arxiv_id":"2505.02489","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-chemical-reaction-and","slug":"enhancing-chemical-reaction-and","title":"Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning","date":"2025-05-05","arxiv_id":"2505.02639","n_code_links":0,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/rewriting-pre-training-data-boosts-llm","slug":"rewriting-pre-training-data-boosts-llm","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","date":"2025-05-05","arxiv_id":"2505.02881","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":["rioyokotalab/swallow-code-math"],"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/txp-reciprocal-generation-of-ground-pressure","slug":"txp-reciprocal-generation-of-ground-pressure","title":"TxP: Reciprocal Generation of Ground Pressure Dynamics and Activity Descriptions for Improving Human Activity Recognition","date":"2025-05-04","arxiv_id":"2505.02052","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-large-language-model-reasoning","title":"Accelerating Large Language Model Reasoning via Speculative Search","date":"2025-05-03","arxiv_id":"2505.02865","n_code_links":0,"syntology":null},{"paper":null,"slug":"physnav-dg-a-novel-adaptive-framework-for","title":"PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applications","date":"2025-05-03","arxiv_id":"2505.01881","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-we-need-a-detailed-rubric-for-automated","title":"Do We Need a Detailed Rubric for Automated Essay Scoring using Large Language Models?","date":"2025-05-02","arxiv_id":"2505.01035","n_code_links":0,"syntology":null},{"paper":null,"slug":"llama-nemotron-efficient-reasoning-models","title":"Llama-Nemotron: Efficient Reasoning Models","date":"2025-05-02","arxiv_id":"2505.00949","n_code_links":0,"syntology":null},{"paper":null,"slug":"pipespec-breaking-stage-dependencies-in","title":"PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding","date":"2025-05-02","arxiv_id":"2505.01572","n_code_links":0,"syntology":null},{"paper":null,"slug":"finescope-precision-pruning-for-domain","title":"FineScope : Precision Pruning for Domain-Specialized Large Language Models Using SAE-Guided Self-Data Cultivation","date":"2025-05-01","arxiv_id":"2505.00624","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-precision-to-perception-user-centred","title":"From Precision to Perception: User-Centred Evaluation of Keyword Extraction Algorithms for Internet-Scale Contextual Advertising","date":"2025-04-30","arxiv_id":"2504.21667","n_code_links":0,"syntology":null},{"paper":null,"slug":"precision-where-it-matters-a-novel-spike","title":"Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models","date":"2025-04-30","arxiv_id":"2504.21553","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-llms-with-amp-attention-heads-and","slug":"efficient-llms-with-amp-attention-heads-and","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","date":"2025-04-29","arxiv_id":"2504.21174","n_code_links":2,"syntology":null},{"paper":null,"slug":"trace-of-thought-prompting-investigating","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","date":"2025-04-29","arxiv_id":"2504.20946","n_code_links":0,"syntology":null},{"paper":null,"slug":"autojudge-judge-decoding-without-manual","title":"AutoJudge: Judge Decoding Without Manual Annotation","date":"2025-04-28","arxiv_id":"2504.20039","n_code_links":0,"syntology":null},{"paper":"/paper/bridge-benchmarking-large-language-models-for","slug":"bridge-benchmarking-large-language-models-for","title":"BRIDGE: Benchmarking Large Language Models for Understanding Real-world Clinical Practice Text","date":"2025-04-28","arxiv_id":"2504.19467","n_code_links":1,"syntology":null},{"paper":null,"slug":"llama-3-1-foundationai-securityllm-base-8b","title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","date":"2025-04-28","arxiv_id":"2504.21039","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-pd-towards-efficient-llm-serving-via","title":"semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage","date":"2025-04-28","arxiv_id":"2504.19867","n_code_links":0,"syntology":null},{"paper":"/paper/can-we-enhance-bug-report-quality-using-llms","slug":"can-we-enhance-bug-report-quality-using-llms","title":"Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation","date":"2025-04-26","arxiv_id":"2504.18804","n_code_links":1,"syntology":null},{"paper":"/paper/clinical-knowledge-in-llms-does-not-translate","slug":"clinical-knowledge-in-llms-does-not-translate","title":"Clinical knowledge in LLMs does not translate to human interactions","date":"2025-04-26","arxiv_id":"2504.18919","n_code_links":1,"syntology":null},{"paper":null,"slug":"effective-length-extrapolation-via-dimension","title":"Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation","date":"2025-04-26","arxiv_id":"2504.18857","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-attacks-on-llm-as-a-judge-systems","title":"Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections","date":"2025-04-25","arxiv_id":"2504.18333","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimism-expectation-or-sarcasm-multi-class","title":"Optimism, Expectation, or Sarcasm? Multi-Class Hope Speech Detection in Spanish and English","date":"2025-04-24","arxiv_id":"2504.17974","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-foundation-model-powered","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","date":"2025-04-23","arxiv_id":"2504.16420","n_code_links":0,"syntology":null},{"paper":null,"slug":"debunking-with-dialogue-exploring-ai","title":"Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theories","date":"2025-04-23","arxiv_id":"2504.16604","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparks-of-tabular-reasoning-via-text2sql","title":"Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning","date":"2025-04-23","arxiv_id":"2505.00016","n_code_links":0,"syntology":null},{"paper":null,"slug":"donod-robust-and-generalizable-instruction","title":"DONOD: Robust and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","date":"2025-04-21","arxiv_id":"2504.14810","n_code_links":0,"syntology":null},{"paper":null,"slug":"keydiff-key-similarity-based-kv-cache","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","date":"2025-04-21","arxiv_id":"2504.15364","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-as-data-annotators-how-close-are-we-to","title":"LLMs as Data Annotators: How Close Are We to Human Performance","date":"2025-04-21","arxiv_id":"2504.15022","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-1st-erel-mir-workshop-on-efficient","title":"The 1st EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval","date":"2025-04-21","arxiv_id":"2504.14788","n_code_links":0,"syntology":null},{"paper":null,"slug":"promptevals-a-dataset-of-assertions-and","title":"PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines","date":"2025-04-20","arxiv_id":"2504.14738","n_code_links":0,"syntology":null},{"paper":null,"slug":"slimpipe-memory-thrifty-and-efficient","title":"SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training","date":"2025-04-20","arxiv_id":"2504.14519","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradual-binary-search-and-dimension-expansion","title":"Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLMs","date":"2025-04-18","arxiv_id":"2504.13989","n_code_links":0,"syntology":null},{"paper":null,"slug":"accuracy-is-not-agreement-expert-aligned","title":"Accuracy is Not Agreement: Expert-Aligned Evaluation of Crash Narrative Classification Models","date":"2025-04-17","arxiv_id":"2504.13068","n_code_links":0,"syntology":null},{"paper":"/paper/chinese-vicuna-a-chinese-instruction","slug":"chinese-vicuna-a-chinese-instruction","title":"Chinese-Vicuna: A Chinese Instruction-following Llama-based Model","date":"2025-04-17","arxiv_id":"2504.12737","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-map-estimation-of-llm-judgment","title":"Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer","date":"2025-04-17","arxiv_id":"2504.12589","n_code_links":0,"syntology":null},{"paper":null,"slug":"main-mutual-alignment-is-necessary-for","title":"MAIN: Mutual Alignment Is Necessary for instruction tuning","date":"2025-04-17","arxiv_id":"2504.12913","n_code_links":0,"syntology":null},{"paper":null,"slug":"memorization-a-close-look-at-books","title":"Memorization: A Close Look at Books","date":"2025-04-17","arxiv_id":"2504.12549","n_code_links":0,"syntology":null},{"paper":null,"slug":"characterizing-and-optimizing-llm-inference","title":"Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures","date":"2025-04-16","arxiv_id":"2504.11750","n_code_links":0,"syntology":null},{"paper":null,"slug":"agmmu-a-comprehensive-agricultural-multimodal","title":"AgMMU: A Comprehensive Agricultural Multimodal Understanding and Reasoning Benchmark","date":"2025-04-14","arxiv_id":"2504.10568","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-chains-of-thought-benchmarking-latent","title":"Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models","date":"2025-04-14","arxiv_id":"2504.10615","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-handle-webshell-detection-overcoming","title":"Can LLMs handle WebShell detection? Overcoming Detection Challenges with Behavioral Function-Aware Framework","date":"2025-04-14","arxiv_id":"2504.13811","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-ve-changed-detecting-modification-of","title":"You've Changed: Detecting Modification of Black-Box Large Language Models","date":"2025-04-14","arxiv_id":"2504.12335","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-learning-with-layer-skipping","title":"Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP","date":"2025-04-13","arxiv_id":"2504.10536","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-tokens-deserve-more-attention","title":"Question Tokens Deserve More Attention: Enhancing Large Language Models without Training through Step-by-Step Reading and Question Attention Recalibration","date":"2025-04-13","arxiv_id":"2504.09402","n_code_links":0,"syntology":null},{"paper":null,"slug":"reconstructing-sepsis-trajectories-from","title":"Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis","date":"2025-04-12","arxiv_id":"2504.12326","n_code_links":0,"syntology":null},{"paper":"/paper/ai-university-an-llm-based-platform-for","slug":"ai-university-an-llm-based-platform-for","title":"AI-University: An LLM-based platform for instructional alignment to scientific classrooms","date":"2025-04-11","arxiv_id":"2504.08846","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-bias-in-llms-for-surveying","title":"Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in Healthcare","date":"2025-04-11","arxiv_id":"2504.08260","n_code_links":0,"syntology":null},{"paper":"/paper/x-guard-multilingual-guard-agent-for-content","slug":"x-guard-multilingual-guard-agent-for-content","title":"X-Guard: Multilingual Guard Agent for Content Moderation","date":"2025-04-11","arxiv_id":"2504.08848","n_code_links":1,"syntology":null},{"paper":null,"slug":"pangu-ultra-pushing-the-limits-of-dense-large","title":"Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs","date":"2025-04-10","arxiv_id":"2504.07866","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-retrieval-augmented-generative","title":"Evaluating Retrieval Augmented Generative Models for Document Queries in Transportation Safety","date":"2025-04-09","arxiv_id":"2504.07022","n_code_links":0,"syntology":null},{"paper":null,"slug":"optuna-vs-code-llama-are-llms-a-new-paradigm","title":"Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?","date":"2025-04-08","arxiv_id":"2504.06006","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-effectiveness-and-generalization-of","title":"On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions","date":"2025-04-07","arxiv_id":"2504.06303","n_code_links":0,"syntology":null},{"paper":"/paper/prima-cpp-speeding-up-70b-scale-llm-inference","slug":"prima-cpp-speeding-up-70b-scale-llm-inference","title":"PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters","date":"2025-04-07","arxiv_id":"2504.08791","n_code_links":1,"syntology":null},{"paper":"/paper/quantization-hurts-reasoning-an-empirical","slug":"quantization-hurts-reasoning-an-empirical","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","date":"2025-04-07","arxiv_id":"2504.04823","n_code_links":1,"syntology":null},{"paper":null,"slug":"opencodeinstruct-a-large-scale-instruction","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","date":"2025-04-05","arxiv_id":"2504.04030","n_code_links":0,"syntology":null},{"paper":null,"slug":"metamorphic-testing-for-fairness-evaluation","title":"Metamorphic Testing for Fairness Evaluation in Large Language Models: Identifying Intersectional Bias in LLaMA and GPT","date":"2025-04-04","arxiv_id":"2504.07982","n_code_links":0,"syntology":null},{"paper":null,"slug":"neutralizing-the-narrative-ai-powered","title":"Neutralizing the Narrative: AI-Powered Debiasing of Online News Articles","date":"2025-04-04","arxiv_id":"2504.03520","n_code_links":0,"syntology":null},{"paper":"/paper/yalenlp-peranssumm-2025-multi-perspective-1","slug":"yalenlp-peranssumm-2025-multi-perspective-1","title":"YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization","date":"2025-04-04","arxiv_id":"2504.03932","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-self-learning-agent-with-a-progressive","title":"The Self-Learning Agent with a Progressive Neural Network Integrated Transformer","date":"2025-04-03","arxiv_id":"2504.02489","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-model-selection-for-time-series","title":"Efficient Model Selection for Time Series Forecasting via LLMs","date":"2025-04-02","arxiv_id":"2504.02119","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolving-security-in-llms-a-study-of","title":"Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses","date":"2025-04-02","arxiv_id":"2504.02080","n_code_links":0,"syntology":null},{"paper":null,"slug":"subasa-adapting-language-models-for-low","title":"Subasa -- Adapting Language Models for Low-resourced Offensive Language Detection in Sinhala","date":"2025-04-02","arxiv_id":"2504.02178","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-reasoning-meets-compression-benchmarking","title":"When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks","date":"2025-04-02","arxiv_id":"2504.02010","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-ptsd-in-clinical-interviews-a","title":"Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models","date":"2025-04-01","arxiv_id":"2504.01216","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-llama-3-2-vision-by-trimming-cross","title":"Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features","date":"2025-04-01","arxiv_id":"2504.00557","n_code_links":0,"syntology":null},{"paper":null,"slug":"thebluescrubs-v1-a-comprehensive-curated","title":"TheBlueScrubs-v1, a comprehensive curated medical dataset derived from the internet","date":"2025-04-01","arxiv_id":"2504.02874","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-systematic-evaluation-of-llm-strategies-for","title":"A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG","date":"2025-03-31","arxiv_id":"2503.24307","n_code_links":0,"syntology":null},{"paper":null,"slug":"ferg-llm-feature-engineering-by-reason","title":"FeRG-LLM : Feature Engineering by Reason Generation Large Language Models","date":"2025-03-30","arxiv_id":"2503.23371","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-better-logical","slug":"large-language-models-are-better-logical","title":"Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation","date":"2025-03-30","arxiv_id":"2503.23363","n_code_links":1,"syntology":null},{"paper":"/paper/promptdistill-query-based-selective-token","slug":"promptdistill-query-based-selective-token","title":"PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference","date":"2025-03-30","arxiv_id":"2503.23274","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-machine-learning-with-large","slug":"multimodal-machine-learning-with-large","title":"Multimodal machine learning with large language embedding model for polymer property prediction","date":"2025-03-29","arxiv_id":"2503.22962","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalization-bias-in-large-language-model","title":"Generalization Bias in Large Language Model Summarization of Scientific Research","date":"2025-03-28","arxiv_id":"2504.00025","n_code_links":0,"syntology":null},{"paper":"/paper/stade-standard-deviation-as-a-pruning-metric","slug":"stade-standard-deviation-as-a-pruning-metric","title":"STADE: Standard Deviation as a Pruning Metric","date":"2025-03-28","arxiv_id":"2503.22451","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-inequality-of-llm-fact-checking","title":"Understanding Inequality of LLM Fact-Checking over Geographic Regions with Agent and Retrieval models","date":"2025-03-28","arxiv_id":"2503.22877","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-for-5","title":"Evaluating Large Language Models for Automated Clinical Abstraction in Pulmonary Embolism Registries: Performance Across Model Sizes, Versions, and Parameters","date":"2025-03-26","arxiv_id":"2503.21004","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-beyond-limits-advances-and-open","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","date":"2025-03-26","arxiv_id":"2503.22732","n_code_links":0,"syntology":null},{"paper":null,"slug":"susceptibility-of-large-language-models-to","title":"Susceptibility of Large Language Models to User-Driven Factors in Medical Queries","date":"2025-03-26","arxiv_id":"2503.22746","n_code_links":0,"syntology":null},{"paper":"/paper/bibliopage-a-dataset-of-scanned-title-pages","slug":"bibliopage-a-dataset-of-scanned-title-pages","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","date":"2025-03-25","arxiv_id":"2503.19658","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-multi-modal-reasoning-llms-work-as","title":"Can Multi-modal (reasoning) LLMs work as deepfake detectors?","date":"2025-03-25","arxiv_id":"2503.20084","n_code_links":0,"syntology":null},{"paper":"/paper/cross-tokenizer-distillation-via-approximate","slug":"cross-tokenizer-distillation-via-approximate","title":"Cross-Tokenizer Distillation via Approximate Likelihood Matching","date":"2025-03-25","arxiv_id":"2503.20083","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 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bminixhofer/alm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"efficient-model-development-through-fine","title":"Efficient Model Development through Fine-tuning Transfer","date":"2025-03-25","arxiv_id":"2503.20110","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-training-and-inference-scaling-laws","slug":"exploring-training-and-inference-scaling-laws","title":"Exploring Training and Inference Scaling Laws in Generative Retrieval","date":"2025-03-24","arxiv_id":"2503.18941","n_code_links":1,"syntology":null}],"record_sha256":"c8e3525ab603c78ce0cfbcc5f542db5d91c660b1ffccc0853136082f888e2b86","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}