{"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/6","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":6,"pages_in_order":11,"rows_per_page":100,"rows":[501,600],"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/5","next":"/method/llama/papers/7","papers":[{"paper":"/paper/tulu-3-pushing-frontiers-in-open-language","slug":"tulu-3-pushing-frontiers-in-open-language","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","date":"2024-11-22","arxiv_id":"2411.15124","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/open-instruct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-detection-of-watermarks-for-large","slug":"robust-detection-of-watermarks-for-large","title":"Robust Detection of Watermarks for Large Language Models Under Human Edits","date":"2024-11-21","arxiv_id":"2411.13868","n_code_links":1,"syntology":null},{"paper":"/paper/star-agents-automatic-data-optimization-with","slug":"star-agents-automatic-data-optimization-with","title":"Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning","date":"2024-11-21","arxiv_id":"2411.14497","n_code_links":1,"syntology":null},{"paper":null,"slug":"are-large-language-models-memorizing-bug","title":"Are Large Language Models Memorizing Bug Benchmarks?","date":"2024-11-20","arxiv_id":"2411.13323","n_code_links":0,"syntology":null},{"paper":"/paper/combining-autoregressive-and-autoencoder","slug":"combining-autoregressive-and-autoencoder","title":"Combining Autoregressive and Autoencoder Language Models for Text Classification","date":"2024-11-20","arxiv_id":"2411.13282","n_code_links":1,"syntology":null},{"paper":"/paper/deriving-activation-functions-via-integration","slug":"deriving-activation-functions-via-integration","title":"Deriving Activation Functions Using Integration","date":"2024-11-20","arxiv_id":"2411.13010","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-llms-capabilities-towards","title":"Evaluating LLMs Capabilities Towards Understanding Social Dynamics","date":"2024-11-20","arxiv_id":"2411.13008","n_code_links":0,"syntology":null},{"paper":"/paper/dlbacktrace-a-model-agnostic-explainability","slug":"dlbacktrace-a-model-agnostic-explainability","title":"DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models","date":"2024-11-19","arxiv_id":"2411.12643","n_code_links":1,"syntology":null},{"paper":"/paper/predicting-user-intents-and-musical","slug":"predicting-user-intents-and-musical","title":"Predicting User Intents and Musical Attributes from Music Discovery Conversations","date":"2024-11-19","arxiv_id":"2411.12254","n_code_links":1,"syntology":null},{"paper":"/paper/redpajama-an-open-dataset-for-training-large","slug":"redpajama-an-open-dataset-for-training-large","title":"RedPajama: an Open Dataset for Training Large Language Models","date":"2024-11-19","arxiv_id":"2411.12372","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["togethercomputer/redpajama-data"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"when-backdoors-speak-understanding-llm","title":"When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations","date":"2024-11-19","arxiv_id":"2411.12701","n_code_links":0,"syntology":null},{"paper":null,"slug":"addressing-hallucinations-in-language-models","title":"Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality","date":"2024-11-18","arxiv_id":"2411.11531","n_code_links":0,"syntology":null},{"paper":null,"slug":"llama-guard-3-1b-int4-compact-and-efficient","title":"Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations","date":"2024-11-18","arxiv_id":"2411.17713","n_code_links":0,"syntology":null},{"paper":"/paper/perfcodegen-improving-performance-of-llm","slug":"perfcodegen-improving-performance-of-llm","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","date":"2024-11-18","arxiv_id":"2412.03578","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"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":["SalesforceAIResearch/perfcodegen"],"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":"transcending-language-boundaries-harnessing","title":"Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation","date":"2024-11-18","arxiv_id":"2411.11295","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-llms-as-traffic-control","title":"Large Language Models (LLMs) as Traffic Control Systems at Urban Intersections: A New Paradigm","date":"2024-11-16","arxiv_id":"2411.10869","n_code_links":0,"syntology":null},{"paper":"/paper/information-extraction-from-clinical-notes","slug":"information-extraction-from-clinical-notes","title":"Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?","date":"2024-11-15","arxiv_id":"2411.10020","n_code_links":1,"syntology":null},{"paper":null,"slug":"jal-anveshak-prediction-of-fishing-zones","title":"Jal Anveshak: Prediction of fishing zones using fine-tuned LlaMa 2","date":"2024-11-15","arxiv_id":"2411.10050","n_code_links":0,"syntology":null},{"paper":null,"slug":"llama-guard-3-vision-safeguarding-human-ai","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","date":"2024-11-15","arxiv_id":"2411.10414","n_code_links":0,"syntology":null},{"paper":"/paper/mlan-language-based-instruction-tuning","slug":"mlan-language-based-instruction-tuning","title":"MLAN: Language-Based Instruction Tuning Improves Zero-Shot Generalization of Multimodal Large Language Models","date":"2024-11-15","arxiv_id":"2411.10557","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompting-and-fine-tuning-large-language","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","date":"2024-11-15","arxiv_id":"2411.10129","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-information-theoretic-approach-to-14","title":"Towards Operationalizing Right to Data Protection","date":"2024-11-13","arxiv_id":"2411.08506","n_code_links":0,"syntology":null},{"paper":null,"slug":"refining-translations-with-llms-a-constraint","title":"Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach","date":"2024-11-13","arxiv_id":"2411.08348","n_code_links":0,"syntology":null},{"paper":"/paper/refusal-in-llms-is-an-affine-function","slug":"refusal-in-llms-is-an-affine-function","title":"Refusal in LLMs is an Affine Function","date":"2024-11-13","arxiv_id":"2411.09003","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":6,"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) · 4 unverified","official":{"repos":["eleutherai/steering-llama3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-evaluating-large-language-models-for","title":"Towards Evaluating Large Language Models for Graph Query Generation","date":"2024-11-13","arxiv_id":"2411.08449","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-low-bit-communication-for-tensor","title":"Towards Low-bit Communication for Tensor Parallel LLM Inference","date":"2024-11-12","arxiv_id":"2411.07942","n_code_links":0,"syntology":null},{"paper":null,"slug":"ambient-ai-scribing-support-comparing-the","title":"Ambient AI Scribing Support: Comparing the Performance of Specialized AI Agentic Architecture to Leading Foundational Models","date":"2024-11-11","arxiv_id":"2411.06713","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-adaptive-optimization-via-subset","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","date":"2024-11-11","arxiv_id":"2411.07120","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-in-medical-informatics","title":"Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding","date":"2024-11-11","arxiv_id":"2411.06823","n_code_links":0,"syntology":null},{"paper":"/paper/llm-neo-parameter-efficient-knowledge","slug":"llm-neo-parameter-efficient-knowledge","title":"LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models","date":"2024-11-11","arxiv_id":"2411.06839","n_code_links":2,"syntology":{"ran":12,"of":12,"n_ran_checked":10,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"pdc-dm-sft-a-road-for-llm-sql-bug-fix","title":"PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing","date":"2024-11-11","arxiv_id":"2411.06767","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-large-language-model-training-1","title":"Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator","date":"2024-11-10","arxiv_id":"2411.06465","n_code_links":0,"syntology":null},{"paper":null,"slug":"keyb2-selecting-key-blocks-is-also-important","title":"KeyB2: Selecting Key Blocks is Also Important for Long Document Ranking with Large Language Models","date":"2024-11-09","arxiv_id":"2411.06254","n_code_links":0,"syntology":null},{"paper":null,"slug":"smart-llama-two-stage-post-training-of-large","title":"Smart-LLaMA: Two-Stage Post-Training of Large Language Models for Smart Contract Vulnerability Detection and Explanation","date":"2024-11-09","arxiv_id":"2411.06221","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-efficient-protein-language-models","title":"Energy Efficient Protein Language Models: Leveraging Small Language Models with LoRA for Controllable Protein Generation","date":"2024-11-08","arxiv_id":"2411.05966","n_code_links":0,"syntology":null},{"paper":null,"slug":"intellectual-property-protection-for-deep-1","title":"Intellectual Property Protection for Deep Learning Model and Dataset Intelligence","date":"2024-11-07","arxiv_id":"2411.05051","n_code_links":0,"syntology":null},{"paper":"/paper/llm2clip-powerful-language-model-unlock","slug":"llm2clip-powerful-language-model-unlock","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation","date":"2024-11-07","arxiv_id":"2411.04997","n_code_links":1,"syntology":null},{"paper":"/paper/zipnn-lossless-compression-for-ai-models","slug":"zipnn-lossless-compression-for-ai-models","title":"ZipNN: Lossless Compression for AI Models","date":"2024-11-07","arxiv_id":"2411.05239","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zipnn/zipnn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-comparative-study-of-recent-large-language","title":"A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients","date":"2024-11-06","arxiv_id":"2411.03805","n_code_links":0,"syntology":null},{"paper":"/paper/can-custom-models-learn-in-context-an","slug":"can-custom-models-learn-in-context-an","title":"Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks","date":"2024-11-06","arxiv_id":"2411.03945","n_code_links":1,"syntology":null},{"paper":null,"slug":"crystal-illuminating-llm-abilities-on","title":"Crystal: Illuminating LLM Abilities on Language and Code","date":"2024-11-06","arxiv_id":"2411.04156","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bilingual-capabilities-of-language","title":"Improving Bilingual Capabilities of Language Models to Support Diverse Linguistic Practices in Education","date":"2024-11-06","arxiv_id":"2411.04308","n_code_links":0,"syntology":null},{"paper":"/paper/improving-radiology-report-conciseness-and","slug":"improving-radiology-report-conciseness-and","title":"Improving Radiology Report Conciseness and Structure via Local Large Language Models","date":"2024-11-06","arxiv_id":"2411.05042","n_code_links":1,"syntology":null},{"paper":null,"slug":"unfair-alignment-examining-safety-alignment","title":"Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models","date":"2024-11-06","arxiv_id":"2411.04291","n_code_links":0,"syntology":null},{"paper":null,"slug":"dafny-annotator-ai-assisted-verification-of","title":"dafny-annotator: AI-Assisted Verification of Dafny Programs","date":"2024-11-05","arxiv_id":"2411.15143","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-benefits-of-domain-pretraining","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictor-corrector-enhanced-transformers","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","date":"2024-11-05","arxiv_id":"2411.03042","n_code_links":0,"syntology":null},{"paper":"/paper/stochastic-monkeys-at-play-random","slug":"stochastic-monkeys-at-play-random","title":"Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment","date":"2024-11-05","arxiv_id":"2411.02785","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-multiple-dimensions-of","title":"Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control","date":"2024-11-04","arxiv_id":"2411.02461","n_code_links":0,"syntology":null},{"paper":"/paper/tablegpt2-a-large-multimodal-model-with","slug":"tablegpt2-a-large-multimodal-model-with","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","date":"2024-11-04","arxiv_id":"2411.02059","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tablegpt/tablegpt-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"high-performance-automated-abstract-screening","title":"High-performance automated abstract screening with large language model ensembles","date":"2024-11-03","arxiv_id":"2411.02451","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-large-language-models-for-1","slug":"investigating-large-language-models-for-1","title":"Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups","date":"2024-11-03","arxiv_id":"2411.01706","n_code_links":1,"syntology":null},{"paper":null,"slug":"interacting-large-language-model-agents","title":"Interacting Large Language Model Agents. Interpretable Models and Social Learning","date":"2024-11-02","arxiv_id":"2411.01271","n_code_links":0,"syntology":null},{"paper":"/paper/todo-enhancing-llm-alignment-with-ternary","slug":"todo-enhancing-llm-alignment-with-ternary","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","date":"2024-11-02","arxiv_id":"2411.02442","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"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":["xxares/todo"],"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":"attackqa-development-and-adoption-of-a","title":"AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs","date":"2024-11-01","arxiv_id":"2411.01073","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-make-trade-offs-involving-stipulated","title":"Can LLMs make trade-offs involving stipulated pain and pleasure states?","date":"2024-11-01","arxiv_id":"2411.02432","n_code_links":0,"syntology":null},{"paper":"/paper/emoji-attack-a-method-for-misleading-judge","slug":"emoji-attack-a-method-for-misleading-judge","title":"Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection","date":"2024-11-01","arxiv_id":"2411.01077","n_code_links":1,"syntology":null},{"paper":"/paper/lingma-swe-gpt-an-open-development-process","slug":"lingma-swe-gpt-an-open-development-process","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","date":"2024-11-01","arxiv_id":"2411.00622","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["LingmaTongyi/Lingma-SWE-GPT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-evolved-reward-learning-for-llms","slug":"self-evolved-reward-learning-for-llms","title":"Self-Evolved Reward Learning for LLMs","date":"2024-11-01","arxiv_id":"2411.00418","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/simplefsdp-simpler-fully-sharded-data","slug":"simplefsdp-simpler-fully-sharded-data","title":"SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compile","date":"2024-11-01","arxiv_id":"2411.00284","n_code_links":2,"syntology":null},{"paper":"/paper/sled-self-logits-evolution-decoding-for","slug":"sled-self-logits-evolution-decoding-for","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","date":"2024-11-01","arxiv_id":"2411.02433","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["JayZhang42/SLED"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"automating-quantum-software-maintenance","title":"Automating Quantum Software Maintenance: Flakiness Detection and Root Cause Analysis","date":"2024-10-31","arxiv_id":"2410.23578","n_code_links":0,"syntology":null},{"paper":null,"slug":"desert-camels-and-oil-sheikhs-arab-centric","title":"Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs","date":"2024-10-31","arxiv_id":"2410.24049","n_code_links":0,"syntology":null},{"paper":null,"slug":"leaf-learning-and-evaluation-augmented-by","title":"LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models","date":"2024-10-31","arxiv_id":"2410.23526","n_code_links":0,"syntology":null},{"paper":"/paper/llm-inference-bench-inference-benchmarking-of","slug":"llm-inference-bench-inference-benchmarking-of","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","date":"2024-10-31","arxiv_id":"2411.00136","n_code_links":1,"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":["argonne-lcf/llm-inference-bench"],"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":null,"slug":"the-potential-of-llms-in-medical-education","title":"The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams","date":"2024-10-31","arxiv_id":"2410.23769","n_code_links":0,"syntology":null},{"paper":"/paper/protransformer-robustify-transformers-via","slug":"protransformer-robustify-transformers-via","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","date":"2024-10-30","arxiv_id":"2410.23182","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-feedback-in-math-education-a","title":"Automated Feedback in Math Education: A Comparative Analysis of LLMs for Open-Ended Responses","date":"2024-10-29","arxiv_id":"2411.08910","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-adversarial-attacks-through-chain","slug":"enhancing-adversarial-attacks-through-chain","title":"Enhancing Adversarial Attacks through Chain of Thought","date":"2024-10-29","arxiv_id":"2410.21791","n_code_links":1,"syntology":null},{"paper":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","n_code_links":0,"syntology":null},{"paper":null,"slug":"get-large-language-models-ready-to-speak-a","title":"Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation","date":"2024-10-27","arxiv_id":"2410.20336","n_code_links":0,"syntology":null},{"paper":"/paper/llama-scope-extracting-millions-of-features","slug":"llama-scope-extracting-millions-of-features","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","date":"2024-10-27","arxiv_id":"2410.20526","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openmoss/language-model-saes"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm-robustness-against-misinformation-in","slug":"llm-robustness-against-misinformation-in","title":"LLM Robustness Against Misinformation in Biomedical Question Answering","date":"2024-10-27","arxiv_id":"2410.21330","n_code_links":1,"syntology":null},{"paper":"/paper/model-equality-testing-which-model-is-this","slug":"model-equality-testing-which-model-is-this","title":"Model Equality Testing: Which Model Is This API Serving?","date":"2024-10-26","arxiv_id":"2410.20247","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"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) · 0 unverified","official":{"repos":["i-gao/model-equality-testing"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reasoning-or-a-semblance-of-it-a-diagnostic","title":"Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs","date":"2024-10-26","arxiv_id":"2410.20200","n_code_links":0,"syntology":null},{"paper":null,"slug":"safe-setup-for-generative-molecular-design","title":"SAFE setup for generative molecular design","date":"2024-10-26","arxiv_id":"2410.20232","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-like-functional-organization-within","title":"Brain-like Functional Organization within Large Language Models","date":"2024-10-25","arxiv_id":"2410.19542","n_code_links":0,"syntology":null},{"paper":null,"slug":"tailored-llama-optimizing-few-shot-learning","title":"Tailored-LLaMA: Optimizing Few-Shot Learning in Pruned LLaMA Models with Task-Specific Prompts","date":"2024-10-24","arxiv_id":"2410.19185","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-the-effective-context-length-of-llms","title":"Why Does the Effective Context Length of LLMs Fall Short?","date":"2024-10-24","arxiv_id":"2410.18745","n_code_links":0,"syntology":null},{"paper":"/paper/asynchronous-rlhf-faster-and-more-efficient","slug":"asynchronous-rlhf-faster-and-more-efficient","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","date":"2024-10-23","arxiv_id":"2410.18252","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["mnoukhov/async_rlhf"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"locating-information-in-large-language-models","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","date":"2024-10-23","arxiv_id":"2410.17770","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-hallucination-gaps-in-large","title":"Multilingual Hallucination Gaps in Large Language Models","date":"2024-10-23","arxiv_id":"2410.18270","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-statistical-analysis-of-llms-self","title":"A Statistical Analysis of LLMs' Self-Evaluation Using Proverbs","date":"2024-10-22","arxiv_id":"2410.16640","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-attention-to-activation-unravelling-the","title":"From Attention to Activation: Unravelling the Enigmas of Large Language Models","date":"2024-10-22","arxiv_id":"2410.17174","n_code_links":0,"syntology":null},{"paper":"/paper/representation-shattering-in-transformers-a","slug":"representation-shattering-in-transformers-a","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","date":"2024-10-22","arxiv_id":"2410.17194","n_code_links":0,"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":null}},{"paper":null,"slug":"revealing-hidden-bias-in-ai-lessons-from","title":"Revealing Hidden Bias in AI: Lessons from Large Language Models","date":"2024-10-22","arxiv_id":"2410.16927","n_code_links":0,"syntology":null},{"paper":"/paper/towards-automated-penetration-testing","slug":"towards-automated-penetration-testing","title":"Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements","date":"2024-10-22","arxiv_id":"2410.17141","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-llms-write-like-humans-variation-in","title":"Do LLMs write like humans? Variation in grammatical and rhetorical styles","date":"2024-10-21","arxiv_id":"2410.16107","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-in-computer-science","slug":"large-language-models-in-computer-science","title":"Large Language Models in Computer Science Education: A Systematic Literature Review","date":"2024-10-21","arxiv_id":"2410.16349","n_code_links":1,"syntology":null},{"paper":"/paper/natural-galore-accelerating-galore-for-memory","slug":"natural-galore-accelerating-galore-for-memory","title":"Natural GaLore: Accelerating GaLore for memory-efficient LLM Training and Fine-tuning","date":"2024-10-21","arxiv_id":"2410.16029","n_code_links":1,"syntology":null},{"paper":null,"slug":"transit-pulse-utilizing-social-media-as-a","title":"Transit Pulse: Utilizing Social Media as a Source for Customer Feedback and Information Extraction with Large Language Model","date":"2024-10-19","arxiv_id":"2410.15016","n_code_links":0,"syntology":null},{"paper":null,"slug":"electrocardiogram-language-model-for-few-shot","title":"Electrocardiogram-Language Model for Few-Shot Question Answering with Meta Learning","date":"2024-10-18","arxiv_id":"2410.14464","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-quantized-large-language-models-1","slug":"evaluating-quantized-large-language-models-1","title":"Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks","date":"2024-10-18","arxiv_id":"2410.14766","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-view-of-delta-parameter-editing-in","title":"A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models","date":"2024-10-17","arxiv_id":"2410.13841","n_code_links":0,"syntology":null},{"paper":"/paper/active-dormant-attention-heads","slug":"active-dormant-attention-heads","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","date":"2024-10-17","arxiv_id":"2410.13835","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":6,"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) · 5 unverified","official":{"repos":["guotianyu2000/active-dormant-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"better-to-ask-in-english-evaluation-of-large","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","date":"2024-10-17","arxiv_id":"2410.13153","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-narrative-driven","title":"Large Language Models as Narrative-Driven Recommenders","date":"2024-10-17","arxiv_id":"2410.13604","n_code_links":0,"syntology":null},{"paper":null,"slug":"comet-towards-partical-w4a4kv4-llms-serving","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","date":"2024-10-16","arxiv_id":"2410.12168","n_code_links":0,"syntology":null},{"paper":null,"slug":"communication-efficient-and-tensorized","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","date":"2024-10-16","arxiv_id":"2410.13097","n_code_links":0,"syntology":null},{"paper":"/paper/daq-density-aware-post-training-weight-only","slug":"daq-density-aware-post-training-weight-only","title":"DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs","date":"2024-10-16","arxiv_id":"2410.12187","n_code_links":1,"syntology":null}],"record_sha256":"8fb7034beefbb4b5792d3ed7a820cde2774fde40f6252590e15e064e8dabc61d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}