{"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/4","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":4,"pages_in_order":11,"rows_per_page":100,"rows":[301,400],"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/papers/3","next":"/method/llama/papers/5","papers":[{"paper":"/paper/tumlu-a-unified-and-native-language","slug":"tumlu-a-unified-and-native-language","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","date":"2025-02-16","arxiv_id":"2502.11020","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-encoder-knows-more-than-you","slug":"multilingual-encoder-knows-more-than-you","title":"Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages","date":"2025-02-15","arxiv_id":"2502.10852","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-the-rationality-of-ai-decision","title":"Benchmarking the rationality of AI decision making using the transitivity axiom","date":"2025-02-14","arxiv_id":"2502.10554","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-for-25","slug":"leveraging-large-language-models-for-25","title":"Leveraging large language models for structured information extraction from pathology reports","date":"2025-02-14","arxiv_id":"2502.12183","n_code_links":1,"syntology":null},{"paper":"/paper/roste-an-efficient-quantization-aware","slug":"roste-an-efficient-quantization-aware","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","date":"2025-02-13","arxiv_id":"2502.09003","n_code_links":0,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 5 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) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/square-sequential-question-answering","slug":"square-sequential-question-answering","title":"SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models","date":"2025-02-13","arxiv_id":"2502.09390","n_code_links":1,"syntology":null},{"paper":"/paper/the-hidden-dimensions-of-llm-alignment-a","slug":"the-hidden-dimensions-of-llm-alignment-a","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Safety Analysis","date":"2025-02-13","arxiv_id":"2502.09674","n_code_links":3,"syntology":null},{"paper":"/paper/cancer-vaccine-adjuvant-name-recognition-from","slug":"cancer-vaccine-adjuvant-name-recognition-from","title":"Cancer Vaccine Adjuvant Name Recognition from Biomedical Literature using Large Language Models","date":"2025-02-12","arxiv_id":"2502.09659","n_code_links":1,"syntology":null},{"paper":null,"slug":"inference-time-sparse-attention-with","title":"Inference-time sparse attention with asymmetric indexing","date":"2025-02-12","arxiv_id":"2502.08246","n_code_links":0,"syntology":null},{"paper":"/paper/automated-capability-discovery-via-model-self","slug":"automated-capability-discovery-via-model-self","title":"Automated Capability Discovery via Model Self-Exploration","date":"2025-02-11","arxiv_id":"2502.07577","n_code_links":2,"syntology":null},{"paper":"/paper/finrl-deepseek-llm-infused-risk-sensitive","slug":"finrl-deepseek-llm-infused-risk-sensitive","title":"FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents","date":"2025-02-11","arxiv_id":"2502.07393","n_code_links":2,"syntology":null},{"paper":"/paper/forget-what-you-know-about-llms-evaluations","slug":"forget-what-you-know-about-llms-evaluations","title":"Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon","date":"2025-02-11","arxiv_id":"2502.07445","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-adaptive-moment-optimization-via","title":"Improving Adaptive Moment Optimization via Preconditioner Diagonalization","date":"2025-02-11","arxiv_id":"2502.07488","n_code_links":0,"syntology":null},{"paper":null,"slug":"nanovlms-how-small-can-we-go-and-still-make","title":"NanoVLMs: How small can we go and still make coherent Vision Language Models?","date":"2025-02-11","arxiv_id":"2502.07838","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-optimizer-design-for-llm","title":"Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension","date":"2025-02-11","arxiv_id":"2502.07752","n_code_links":0,"syntology":null},{"paper":"/paper/transmla-multi-head-latent-attention-is-all","slug":"transmla-multi-head-latent-attention-is-all","title":"TransMLA: Multi-Head Latent Attention Is All You Need","date":"2025-02-11","arxiv_id":"2502.07864","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-systematic-reasoning-abilities","slug":"evaluating-the-systematic-reasoning-abilities","title":"Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring","date":"2025-02-10","arxiv_id":"2502.07087","n_code_links":1,"syntology":null},{"paper":"/paper/let-the-ai-conspiracy-begin-language-model","slug":"let-the-ai-conspiracy-begin-language-model","title":"HSI: Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models","date":"2025-02-09","arxiv_id":"2502.05945","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-effectiveness-of-large-language-models-3","title":"On the Effectiveness of Large Language Models in Automating Categorization of Scientific Texts","date":"2025-02-08","arxiv_id":"2502.15745","n_code_links":0,"syntology":null},{"paper":null,"slug":"refining-positive-and-toxic-samples-for-dual","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions","date":"2025-02-08","arxiv_id":"2502.08657","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-understand-1","title":"Can Large Language Models Understand Intermediate Representations?","date":"2025-02-07","arxiv_id":"2502.06854","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-unintended-memorization-with-lora","slug":"mitigating-unintended-memorization-with-lora","title":"Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs","date":"2025-02-07","arxiv_id":"2502.05087","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoding-ai-judgment-how-llms-assess-news","title":"Decoding AI Judgment: How LLMs Assess News Credibility and Bias","date":"2025-02-06","arxiv_id":"2502.04426","n_code_links":0,"syntology":null},{"paper":"/paper/identify-critical-kv-cache-in-llm-inference","slug":"identify-critical-kv-cache-in-llm-inference","title":"Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective","date":"2025-02-06","arxiv_id":"2502.03805","n_code_links":2,"syntology":{"ran":4,"of":11,"n_ran_checked":3,"n_instrument":1,"unverified":7,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["NVIDIA/kvpress"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"mediator-memory-efficient-llm-merging-with","title":"Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing","date":"2025-02-06","arxiv_id":"2502.04411","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-a-vision-language-action-model-for","title":"Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture","date":"2025-02-06","arxiv_id":"2502.04558","n_code_links":0,"syntology":null},{"paper":null,"slug":"entropy-adaptive-decoding-dynamic-model","title":"Entropy Adaptive Decoding: Dynamic Model Switching for Efficient Inference","date":"2025-02-05","arxiv_id":"2502.06833","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-zero-initialized-attention-optimal-prompt","title":"On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation","date":"2025-02-05","arxiv_id":"2502.03029","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-llms-in-1","title":"Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projects","date":"2025-02-04","arxiv_id":"2502.02368","n_code_links":0,"syntology":null},{"paper":null,"slug":"lv-xattn-distributed-cross-attention-for-long","title":"LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models","date":"2025-02-04","arxiv_id":"2502.02406","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-agentic-ai-workflow-for-detecting","title":"An Agentic AI Workflow for Detecting Cognitive Concerns in Real-world Data","date":"2025-02-03","arxiv_id":"2502.01789","n_code_links":0,"syntology":null},{"paper":null,"slug":"bare-combining-base-and-instruction-tuned","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","date":"2025-02-03","arxiv_id":"2502.01697","n_code_links":0,"syntology":null},{"paper":null,"slug":"discovering-chunks-in-neural-embeddings-for","title":"Discovering Chunks in Neural Embeddings for Interpretability","date":"2025-02-03","arxiv_id":"2502.01803","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-large-language-models-via","slug":"evaluation-of-large-language-models-via","title":"Evaluation of Large Language Models via Coupled Token Generation","date":"2025-02-03","arxiv_id":"2502.01754","n_code_links":1,"syntology":null},{"paper":null,"slug":"selfcheckagent-zero-resource-hallucination","title":"SelfCheckAgent: Zero-Resource Hallucination Detection in Generative Large Language Models","date":"2025-02-03","arxiv_id":"2502.01812","n_code_links":0,"syntology":null},{"paper":null,"slug":"agent-based-uncertainty-awareness-improves","title":"Agent-Based Uncertainty Awareness Improves Automated Radiology Report Labeling with an Open-Source Large Language Model","date":"2025-02-02","arxiv_id":"2502.01691","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-effective-is-constitutional-ai-in-small","title":"How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers","date":"2025-02-01","arxiv_id":"2503.17365","n_code_links":0,"syntology":null},{"paper":null,"slug":"pause-tuning-for-long-context-comprehension-a","title":"Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration","date":"2025-02-01","arxiv_id":"2502.20405","n_code_links":0,"syntology":null},{"paper":"/paper/cache-me-if-you-must-adaptive-key-value","slug":"cache-me-if-you-must-adaptive-key-value","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","date":"2025-01-31","arxiv_id":"2501.19392","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-ai-solve-the-peer-review-crisis-a-large","title":"Can AI Solve the Peer Review Crisis? A Large Scale Cross Model Experiment of LLMs' Performance and Biases in Evaluating over 1000 Economics Papers","date":"2025-01-31","arxiv_id":"2502.00070","n_code_links":0,"syntology":null},{"paper":null,"slug":"deltallm-compress-llms-with-low-rank-deltas","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","date":"2025-01-30","arxiv_id":"2501.18596","n_code_links":0,"syntology":null},{"paper":null,"slug":"genie-generative-note-information-extraction","title":"GENIE: Generative Note Information Extraction model for structuring EHR data","date":"2025-01-30","arxiv_id":"2501.18435","n_code_links":0,"syntology":null},{"paper":"/paper/guardreasoner-towards-reasoning-based-llm","slug":"guardreasoner-towards-reasoning-based-llm","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","date":"2025-01-30","arxiv_id":"2501.18492","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yueliu1999/guardreasoner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"high-accuracy-ecg-image-interpretation-using","title":"High-Accuracy ECG Image Interpretation using Parameter-Efficient LoRA Fine-Tuning with Multimodal LLaMA 3.2","date":"2025-01-30","arxiv_id":"2501.18670","n_code_links":0,"syntology":null},{"paper":null,"slug":"r-i-p-better-models-by-survival-of-the","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","date":"2025-01-30","arxiv_id":"2501.18578","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-assistance-for-pediatric-depression","title":"LLM Assistance for Pediatric Depression","date":"2025-01-29","arxiv_id":"2501.17510","n_code_links":0,"syntology":null},{"paper":null,"slug":"cos-m-o-s-curiosity-and-rl-enhanced-mcts-for","title":"COS(M+O)S: Curiosity and RL-Enhanced MCTS for Exploring Story Space via Language Models","date":"2025-01-28","arxiv_id":"2501.17104","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-autoencoders-trained-on-the-same-data","title":"Sparse Autoencoders Trained on the Same Data Learn Different Features","date":"2025-01-28","arxiv_id":"2501.16615","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-using-large","title":"Evaluating The Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology","date":"2025-01-27","arxiv_id":"2501.16309","n_code_links":0,"syntology":null},{"paper":"/paper/relcat-advancing-extraction-of-clinical-inter","slug":"relcat-advancing-extraction-of-clinical-inter","title":"RelCAT: Advancing Extraction of Clinical Inter-Entity Relationships from Unstructured Electronic Health Records","date":"2025-01-27","arxiv_id":"2501.16077","n_code_links":1,"syntology":null},{"paper":null,"slug":"targeting-alignment-extracting-safety","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","date":"2025-01-27","arxiv_id":"2501.16534","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-tip-of-the-iceberg-revealing-a-hidden","title":"The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs","date":"2025-01-27","arxiv_id":"2501.18626","n_code_links":0,"syntology":null},{"paper":null,"slug":"decentralized-low-rank-fine-tuning-of-large","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","date":"2025-01-26","arxiv_id":"2501.15361","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-estonian-text-simplification","title":"Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets","date":"2025-01-26","arxiv_id":"2501.15624","n_code_links":0,"syntology":null},{"paper":"/paper/patentlmm-large-multimodal-model-for","slug":"patentlmm-large-multimodal-model-for","title":"PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures","date":"2025-01-25","arxiv_id":"2501.15074","n_code_links":1,"syntology":null},{"paper":null,"slug":"clear-minds-think-alike-what-makes-llm-fine","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","date":"2025-01-24","arxiv_id":"2501.14315","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-table-instruction-tuning","slug":"rethinking-table-instruction-tuning","title":"Rethinking Table Instruction Tuning","date":"2025-01-24","arxiv_id":"2501.14693","n_code_links":1,"syntology":null},{"paper":"/paper/medslice-fine-tuned-large-language-models-for","slug":"medslice-fine-tuned-large-language-models-for","title":"MedSlice: Fine-Tuned Large Language Models for Secure Clinical Note Sectioning","date":"2025-01-23","arxiv_id":"2501.14105","n_code_links":1,"syntology":null},{"paper":"/paper/ramqa-a-unified-framework-for-retrieval","slug":"ramqa-a-unified-framework-for-retrieval","title":"RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering","date":"2025-01-23","arxiv_id":"2501.13297","n_code_links":1,"syntology":null},{"paper":"/paper/recall-library-like-behavior-in-language","slug":"recall-library-like-behavior-in-language","title":"RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles","date":"2025-01-23","arxiv_id":"2501.13491","n_code_links":1,"syntology":null},{"paper":"/paper/the-breeze-2-herd-of-models-traditional","slug":"the-breeze-2-herd-of-models-traditional","title":"The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities","date":"2025-01-23","arxiv_id":"2501.13921","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-generative-ai-for-scoring","title":"Benchmarking Generative AI for Scoring Medical Student Interviews in Objective Structured Clinical Examinations (OSCEs)","date":"2025-01-21","arxiv_id":"2501.13957","n_code_links":0,"syntology":null},{"paper":"/paper/can-open-source-large-language-models-be-used","slug":"can-open-source-large-language-models-be-used","title":"Can open source large language models be used for tumor documentation in Germany? -- An evaluation on urological doctors' notes","date":"2025-01-21","arxiv_id":"2501.12106","n_code_links":1,"syntology":null},{"paper":"/paper/episodic-memories-generation-and-evaluation","slug":"episodic-memories-generation-and-evaluation","title":"Episodic Memories Generation and Evaluation Benchmark for Large Language Models","date":"2025-01-21","arxiv_id":"2501.13121","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":13,"n_instrument":0,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ahstat/episodic-memory-benchmark"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-large-language-models-to-enhance-2","title":"Leveraging Large Language Models to Enhance Machine Learning Interpretability and Predictive Performance: A Case Study on Emergency Department Returns for Mental Health Patients","date":"2025-01-21","arxiv_id":"2502.00025","n_code_links":0,"syntology":null},{"paper":null,"slug":"pushing-the-limits-of-bfp-on-narrow-precision","title":"Pushing the Limits of BFP on Narrow Precision LLM Inference","date":"2025-01-21","arxiv_id":"2502.00026","n_code_links":0,"syntology":null},{"paper":"/paper/green-code-optimizing-energy-efficiency-in","slug":"green-code-optimizing-energy-efficiency-in","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","date":"2025-01-19","arxiv_id":"2501.11006","n_code_links":1,"syntology":null},{"paper":null,"slug":"dna-1-0-technical-report","title":"DNA 1.0 Technical Report","date":"2025-01-18","arxiv_id":"2501.10648","n_code_links":0,"syntology":null},{"paper":"/paper/dialogue-benchmark-generation-from-knowledge","slug":"dialogue-benchmark-generation-from-knowledge","title":"Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs","date":"2025-01-17","arxiv_id":"2501.09928","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-for-error-detection-in","slug":"confidence-estimation-for-error-detection-in","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","date":"2025-01-16","arxiv_id":"2501.09527","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-adaptation-of-foundation-llms-for-e","title":"Domain Adaptation of Foundation LLMs for e-Commerce","date":"2025-01-16","arxiv_id":"2501.09706","n_code_links":0,"syntology":null},{"paper":null,"slug":"fasp-fast-and-accurate-structured-pruning-of","title":"FASP: Fast and Accurate Structured Pruning of Large Language Models","date":"2025-01-16","arxiv_id":"2501.09412","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-ethical-logic-of-six-large","title":"Analyzing the Ethical Logic of Six Large Language Models","date":"2025-01-15","arxiv_id":"2501.08951","n_code_links":0,"syntology":null},{"paper":null,"slug":"development-and-validation-of-the-provider","title":"Development and Validation of the Provider Documentation Summarization Quality Instrument for Large Language Models","date":"2025-01-15","arxiv_id":"2501.08977","n_code_links":0,"syntology":null},{"paper":"/paper/idea-image-description-enhanced-clip-adapter","slug":"idea-image-description-enhanced-clip-adapter","title":"IDEA: Image Description Enhanced CLIP-Adapter","date":"2025-01-15","arxiv_id":"2501.08816","n_code_links":1,"syntology":null},{"paper":null,"slug":"consistency-of-responses-and-continuations","title":"Consistency of Responses and Continuations Generated by Large Language Models on Social Media","date":"2025-01-14","arxiv_id":"2501.08102","n_code_links":0,"syntology":null},{"paper":"/paper/pokerbench-training-large-language-models-to","slug":"pokerbench-training-large-language-models-to","title":"PokerBench: Training Large Language Models to become Professional Poker Players","date":"2025-01-14","arxiv_id":"2501.08328","n_code_links":1,"syntology":null},{"paper":null,"slug":"potential-and-perils-of-large-language-models","title":"Potential and Perils of Large Language Models as Judges of Unstructured Textual Data","date":"2025-01-14","arxiv_id":"2501.08167","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-net-democratizing-llms-as-a-service","title":"LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks","date":"2025-01-13","arxiv_id":"2501.07288","n_code_links":0,"syntology":null},{"paper":"/paper/language-fusion-for-parameter-efficient-cross","slug":"language-fusion-for-parameter-efficient-cross","title":"Language Fusion for Parameter-Efficient Cross-lingual Transfer","date":"2025-01-12","arxiv_id":"2501.06892","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-code-generation-with-llms-a-multi","title":"Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks","date":"2025-01-11","arxiv_id":"2501.06625","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-4","title":"Exploring Large Language Models for Translating Romanian Computational Problems into English","date":"2025-01-09","arxiv_id":"2501.05601","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-llms-to-infer-non-binary-covid-19","title":"Using LLMs to Infer Non-Binary COVID-19 Sentiments of Chinese Micro-bloggers","date":"2025-01-09","arxiv_id":"2501.05423","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-and-planning-in-robotic-navigation-a","title":"Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models","date":"2025-01-07","arxiv_id":"2501.05478","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-explainable-ai-for-llm-text","title":"Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text","date":"2025-01-06","arxiv_id":"2501.03212","n_code_links":0,"syntology":null},{"paper":"/paper/chair-classifier-of-hallucination-as-improver","slug":"chair-classifier-of-hallucination-as-improver","title":"CHAIR -- Classifier of Hallucination as Improver","date":"2025-01-05","arxiv_id":"2501.02518","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoding-specialised-feature-neurons-in-llms","title":"Decoding specialised feature neurons in LLMs with the final projection layer","date":"2025-01-05","arxiv_id":"2501.02688","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-models-with-some","title":"A Survey on Large Language Models with some Insights on their Capabilities and Limitations","date":"2025-01-03","arxiv_id":"2501.04040","n_code_links":0,"syntology":null},{"paper":null,"slug":"personaai-leveraging-retrieval-augmented","title":"PersonaAI: Leveraging Retrieval-Augmented Generation and Personalized Context for AI-Driven Digital Avatars","date":"2025-01-03","arxiv_id":"2503.15489","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-mental-health-1","title":"Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case","date":"2025-01-02","arxiv_id":"2501.01305","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-inclusive-educational-ai-auditing","title":"Toward Inclusive Educational AI: Auditing Frontier LLMs through a Multiplexity Lens","date":"2025-01-02","arxiv_id":"2501.03259","n_code_links":0,"syntology":null},{"paper":null,"slug":"igc-integrating-a-gated-calculator-into-an","title":"IGC: Integrating a Gated Calculator into an LLM to Solve Arithmetic Tasks Reliably and Efficiently","date":"2025-01-01","arxiv_id":"2501.00684","n_code_links":0,"syntology":null},{"paper":"/paper/2-olmo-2-furious","slug":"2-olmo-2-furious","title":"2 OLMo 2 Furious","date":"2024-12-31","arxiv_id":"2501.00656","n_code_links":3,"syntology":{"ran":16,"of":21,"n_ran_checked":16,"n_instrument":0,"unverified":5,"pointer_only":2,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["allenai/OLMo-core","allenai/olmes","allenai/olmo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"an-empirical-evaluation-of-large-language","title":"An Empirical Evaluation of Large Language Models on Consumer Health Questions","date":"2024-12-31","arxiv_id":"2501.00208","n_code_links":0,"syntology":null},{"paper":null,"slug":"equator-a-deterministic-framework-for","title":"EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-beta","date":"2024-12-31","arxiv_id":"2501.00257","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-sustainable-large-language-model","title":"Towards Sustainable Large Language Model Serving","date":"2024-12-31","arxiv_id":"2501.01990","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-strategies-for-length-controllable","title":"Zero-Shot Strategies for Length-Controllable Summarization","date":"2024-12-31","arxiv_id":"2501.00233","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-batch-size-schedules-for-distributed","title":"Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism","date":"2024-12-30","arxiv_id":"2412.21124","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-desired-comments-for-enhanced-code","title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","date":"2024-12-29","arxiv_id":"2412.20340","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-weight-normalized-low-rank","slug":"gradient-weight-normalized-low-rank","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","date":"2024-12-27","arxiv_id":"2412.19616","n_code_links":1,"syntology":null}],"record_sha256":"f8756fbf6904dceed1fcce5afe50f8e87a6747931662f68e519f8e3d0fa3d00c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}