{"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/7","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":7,"pages_in_order":11,"rows_per_page":100,"rows":[601,700],"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/6","next":"/method/llama/papers/8","papers":[{"paper":null,"slug":"identifying-task-groupings-for-multi-task","title":"Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information","date":"2024-10-16","arxiv_id":"2410.12774","n_code_links":0,"syntology":null},{"paper":null,"slug":"with-a-grain-of-salt-are-llms-fair-across","title":"With a Grain of SALT: Are LLMs Fair Across Social Dimensions?","date":"2024-10-16","arxiv_id":"2410.12499","n_code_links":0,"syntology":null},{"paper":"/paper/aic-ctu-system-at-averitec-re-framing","slug":"aic-ctu-system-at-averitec-re-framing","title":"AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task","date":"2024-10-15","arxiv_id":"2410.11446","n_code_links":1,"syntology":null},{"paper":null,"slug":"athena-retrieval-augmented-legal-judgment","title":"Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models","date":"2024-10-15","arxiv_id":"2410.11195","n_code_links":0,"syntology":null},{"paper":"/paper/disp-llm-dimension-independent-structural","slug":"disp-llm-dimension-independent-structural","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11988","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":3,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhengaoLi/DISP-LLM-Dimension-Independent-Structural-Pruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"transfer-learning-with-foundational-models","title":"Transfer Learning with Foundational Models for Time Series Forecasting using Low-Rank Adaptations","date":"2024-10-15","arxiv_id":"2410.11539","n_code_links":0,"syntology":null},{"paper":null,"slug":"balancing-continuous-pre-training-and","title":"Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs","date":"2024-10-14","arxiv_id":"2410.10739","n_code_links":0,"syntology":null},{"paper":"/paper/lolcats-on-low-rank-linearizing-of-large","slug":"lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10254","n_code_links":1,"syntology":{"ran":23,"of":32,"n_ran_checked":13,"n_instrument":10,"unverified":9,"pointer_only":0,"phrase":"23 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","official":{"repos":["hazyresearch/lolcats"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":9,"n_ran_no_instrument_failure":13,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"seedlm-compressing-llm-weights-into-seeds-of","title":"SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators","date":"2024-10-14","arxiv_id":"2410.10714","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-dysarthric-speech-leveraging","title":"Empowering Dysarthric Speech: Leveraging Advanced LLMs for Accurate Speech Correction and Multimodal Emotion Analysis","date":"2024-10-13","arxiv_id":"2410.12867","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-of-llms-in-making","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","date":"2024-10-13","arxiv_id":"2410.09992","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-implicit-bias-in-large-language","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","date":"2024-10-13","arxiv_id":"2410.12864","n_code_links":0,"syntology":null},{"paper":"/paper/pear-a-robust-and-flexible-automation","slug":"pear-a-robust-and-flexible-automation","title":"PEAR: A Robust and Flexible Automation Framework for Ptychography Enabled by Multiple Large Language Model Agents","date":"2024-10-11","arxiv_id":"2410.09034","n_code_links":1,"syntology":null},{"paper":null,"slug":"simplestrat-diversifying-language-model","title":"SimpleStrat: Diversifying Language Model Generation with Stratification","date":"2024-10-11","arxiv_id":"2410.09038","n_code_links":0,"syntology":null},{"paper":"/paper/supercorrect-supervising-and-correcting","slug":"supercorrect-supervising-and-correcting","title":"SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights","date":"2024-10-11","arxiv_id":"2410.09008","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["yangling0818/supercorrect-llm"],"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":"crossquant-a-post-training-quantization","title":"CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression","date":"2024-10-10","arxiv_id":"2410.07505","n_code_links":0,"syntology":null},{"paper":"/paper/executing-arithmetic-fine-tuning-large","slug":"executing-arithmetic-fine-tuning-large","title":"Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines","date":"2024-10-10","arxiv_id":"2410.07896","n_code_links":1,"syntology":null},{"paper":null,"slug":"optima-optimizing-effectiveness-and","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","date":"2024-10-10","arxiv_id":"2410.08115","n_code_links":0,"syntology":null},{"paper":"/paper/vibecheck-discover-and-quantify-qualitative","slug":"vibecheck-discover-and-quantify-qualitative","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","date":"2024-10-10","arxiv_id":"2410.12851","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":["lisadunlap/vibecheck"],"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":null,"slug":"do-great-minds-think-alike-investigating","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","date":"2024-10-09","arxiv_id":"2410.06524","n_code_links":0,"syntology":null},{"paper":"/paper/torchtitan-one-stop-pytorch-native-solution","slug":"torchtitan-one-stop-pytorch-native-solution","title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training","date":"2024-10-09","arxiv_id":"2410.06511","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pytorch/torchtitan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"applying-refusal-vector-ablation-to-llama-3-1","title":"Applying Refusal-Vector Ablation to Llama 3.1 70B Agents","date":"2024-10-08","arxiv_id":"2410.10871","n_code_links":0,"syntology":null},{"paper":"/paper/toolbridge-an-open-source-dataset-to-equip","slug":"toolbridge-an-open-source-dataset-to-equip","title":"ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities","date":"2024-10-08","arxiv_id":"2410.10872","n_code_links":1,"syntology":null},{"paper":null,"slug":"causal-micro-narratives","title":"Causal Micro-Narratives","date":"2024-10-07","arxiv_id":"2410.05252","n_code_links":0,"syntology":null},{"paper":null,"slug":"density-estimation-with-llms-a-geometric","title":"Density estimation with LLMs: a geometric investigation of in-context learning trajectories","date":"2024-10-07","arxiv_id":"2410.05218","n_code_links":0,"syntology":null},{"paper":null,"slug":"garlic-llm-guided-dynamic-progress-control","title":"GARLIC: LLM-Guided Dynamic Progress Control with Hierarchical Weighted Graph for Long Document QA","date":"2024-10-07","arxiv_id":"2410.04790","n_code_links":0,"syntology":null},{"paper":null,"slug":"intent-classification-for-bank-chatbots","title":"Intent Classification for Bank Chatbots through LLM Fine-Tuning","date":"2024-10-07","arxiv_id":"2410.04925","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-potential-of-conversational","title":"Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench","date":"2024-10-06","arxiv_id":"2410.04485","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-inference-acceleration-a","slug":"large-language-model-inference-acceleration-a","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","date":"2024-10-06","arxiv_id":"2410.04466","n_code_links":1,"syntology":null},{"paper":"/paper/cs4-measuring-the-creativity-of-large","slug":"cs4-measuring-the-creativity-of-large","title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","date":"2024-10-05","arxiv_id":"2410.04197","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["anirudhlakkaraju/cs4_benchmark"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/commonit-commonality-aware-instruction-tuning","slug":"commonit-commonality-aware-instruction-tuning","title":"CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions","date":"2024-10-04","arxiv_id":"2410.03077","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["raojay7/commonit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-much-can-we-forget-about-data","slug":"how-much-can-we-forget-about-data","title":"How Much Can We Forget about Data Contamination?","date":"2024-10-04","arxiv_id":"2410.03249","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tml-tuebingen/forgetting-contamination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lorc-low-rank-compression-for-llms-kv-cache","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","date":"2024-10-04","arxiv_id":"2410.03111","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-prompts-to-guide-large-language-models","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","date":"2024-10-04","arxiv_id":"2410.03848","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-inference-time-compute-llms-can","title":"Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation","date":"2024-10-03","arxiv_id":"2410.02725","n_code_links":0,"syntology":null},{"paper":"/paper/characterizing-context-influence-and","slug":"characterizing-context-influence-and","title":"Characterizing Context Influence and Hallucination in Summarization","date":"2024-10-03","arxiv_id":"2410.03026","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-as-markov-chains","title":"Large Language Models as Markov Chains","date":"2024-10-03","arxiv_id":"2410.02724","n_code_links":0,"syntology":null},{"paper":"/paper/llama-slayer-8b-shallow-layers-hold-the-key","slug":"llama-slayer-8b-shallow-layers-hold-the-key","title":"Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection","date":"2024-10-03","arxiv_id":"2410.02330","n_code_links":1,"syntology":null},{"paper":null,"slug":"logra-med-long-context-multi-graph-alignment","title":"LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model","date":"2024-10-03","arxiv_id":"2410.02615","n_code_links":0,"syntology":null},{"paper":null,"slug":"safeguard-is-a-double-edged-sword-denial-of","title":"LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks","date":"2024-10-03","arxiv_id":"2410.02916","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-structured-thinking-in-language","title":"Unlocking Structured Thinking in Language Models with Cognitive Prompting","date":"2024-10-03","arxiv_id":"2410.02953","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-red-teaming-with-goat-the","title":"Automated Red Teaming with GOAT: the Generative Offensive Agent Tester","date":"2024-10-02","arxiv_id":"2410.01606","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-aware-response-generation-using","title":"Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation","date":"2024-10-02","arxiv_id":"2410.01306","n_code_links":0,"syntology":null},{"paper":null,"slug":"et-plan-bench-embodied-task-level-planning","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","date":"2024-10-02","arxiv_id":"2410.14682","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-role-of-relationship-alignment","title":"Examining the Role of Relationship Alignment in Large Language Models","date":"2024-10-02","arxiv_id":"2410.01708","n_code_links":0,"syntology":null},{"paper":"/paper/quantifying-generalization-complexity-for","slug":"quantifying-generalization-complexity-for","title":"Quantifying Generalization Complexity for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01769","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhentingqi/scylla"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"small-language-models-like-small-vocabularies","title":"Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas","date":"2024-10-02","arxiv_id":"2410.01487","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-autoencoders-reveal-temporal","title":"Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models","date":"2024-10-02","arxiv_id":"2410.01280","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-suffixes-may-be-features-too","slug":"adversarial-suffixes-may-be-features-too","title":"Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models","date":"2024-10-01","arxiv_id":"2410.00451","n_code_links":1,"syntology":null},{"paper":null,"slug":"causal-representation-learning-with","title":"Causal Representation Learning with Generative Artificial Intelligence: Application to Texts as Treatments","date":"2024-10-01","arxiv_id":"2410.00903","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-hate-exploring-language-models","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","date":"2024-10-01","arxiv_id":"2410.00775","n_code_links":0,"syntology":null},{"paper":"/paper/tpi-llm-serving-70b-scale-llms-efficiently-on","slug":"tpi-llm-serving-70b-scale-llms-efficiently-on","title":"TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices","date":"2024-10-01","arxiv_id":"2410.00531","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-looming-replication-crisis-in-evaluating","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","date":"2024-09-30","arxiv_id":"2409.20303","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-state-of-the","title":"Evaluating the performance of state-of-the-art esg domain-specific pre-trained large language models in text classification against existing models and traditional machine learning techniques","date":"2024-09-30","arxiv_id":"2410.00207","n_code_links":0,"syntology":null},{"paper":null,"slug":"rotated-runtime-smooth-training-free","title":"Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference","date":"2024-09-30","arxiv_id":"2409.20361","n_code_links":0,"syntology":null},{"paper":null,"slug":"gentel-safe-a-unified-benchmark-and-shielding","title":"GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks","date":"2024-09-29","arxiv_id":"2409.19521","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-tokenizers-in-large","title":"Performance Evaluation of Tokenizers in Large Language Models for the Assamese Language","date":"2024-09-28","arxiv_id":"2410.03718","n_code_links":0,"syntology":null},{"paper":null,"slug":"charting-the-future-using-chart-question","title":"Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations","date":"2024-09-27","arxiv_id":"2409.18764","n_code_links":0,"syntology":null},{"paper":"/paper/lml-language-model-learning-a-dataset-for","slug":"lml-language-model-learning-a-dataset-for","title":"LML-DAP: Language Model Learning a Dataset for Data-Augmented Prediction","date":"2024-09-27","arxiv_id":"2409.18957","n_code_links":1,"syntology":null},{"paper":"/paper/read-over-the-lines-attacking-llms-and","slug":"read-over-the-lines-attacking-llms-and","title":"Read Over the Lines: Attacking LLMs and Toxicity Detection Systems with ASCII Art to Mask Profanity","date":"2024-09-27","arxiv_id":"2409.18708","n_code_links":1,"syntology":null},{"paper":null,"slug":"code-generation-and-algorithmic-problem","title":"Code Generation and Algorithmic Problem Solving Using Llama 3.1 405B","date":"2024-09-26","arxiv_id":"2409.19027","n_code_links":0,"syntology":null},{"paper":"/paper/emma-500-enhancing-massively-multilingual","slug":"emma-500-enhancing-massively-multilingual","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","date":"2024-09-26","arxiv_id":"2409.17892","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["MaLA-LM/emma-500"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/extracting-affect-aggregates-from","slug":"extracting-affect-aggregates-from","title":"Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17990","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":["dess-mannheim/temporal-adapters"],"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":"heuristics-and-biases-in-ai-decision-making","title":"Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI","date":"2024-09-26","arxiv_id":"2410.02820","n_code_links":0,"syntology":null},{"paper":null,"slug":"t3-a-novel-zero-shot-transfer-learning","title":"T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task","date":"2024-09-26","arxiv_id":"2409.17640","n_code_links":0,"syntology":null},{"paper":"/paper/counterfactual-token-generation-in-large","slug":"counterfactual-token-generation-in-large","title":"Counterfactual Token Generation in Large Language Models","date":"2024-09-25","arxiv_id":"2409.17027","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["networks-learning/counterfactual-llms"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-disease-detection-in-radiology","title":"Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels","date":"2024-09-25","arxiv_id":"2409.16563","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-guardrails-for-safe-and-secure","title":"Enhancing Guardrails for Safe and Secure Healthcare AI","date":"2024-09-25","arxiv_id":"2409.17190","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-evaluation-of-large-language-3","title":"A Comprehensive Evaluation of Large Language Models on Mental Illnesses","date":"2024-09-24","arxiv_id":"2409.15687","n_code_links":0,"syntology":null},{"paper":null,"slug":"harmonising-the-clinical-melody-tuning-large","title":"Harmonising the Clinical Melody: Tuning Large Language Models for Hospital Course Summarisation in Clinical Coding","date":"2024-09-23","arxiv_id":"2409.14638","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-policy-analysis-through-prompt","title":"Privacy Policy Analysis through Prompt Engineering for LLMs","date":"2024-09-23","arxiv_id":"2409.14879","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-realistic-long-term-benchmark-for","title":"Towards a Realistic Long-Term Benchmark for Open-Web Research Agents","date":"2024-09-23","arxiv_id":"2409.14913","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-racial-and-age-biases-in","title":"Evaluating Gender, Racial, and Age Biases in Large Language Models: A Comparative Analysis of Occupational and Crime Scenarios","date":"2024-09-22","arxiv_id":"2409.14583","n_code_links":0,"syntology":null},{"paper":null,"slug":"2409-13870","title":"Instruct-Tuning Pretrained Causal Language Models for Ancient Greek Papyrology and Epigraphy","date":"2024-09-20","arxiv_id":"2409.13870","n_code_links":0,"syntology":null},{"paper":"/paper/stop-benchmarking-large-language-models-with","slug":"stop-benchmarking-large-language-models-with","title":"STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions","date":"2024-09-20","arxiv_id":"2409.13843","n_code_links":1,"syntology":null},{"paper":null,"slug":"are-large-language-models-good-essay-graders","title":"Are Large Language Models Good Essay Graders?","date":"2024-09-19","arxiv_id":"2409.13120","n_code_links":0,"syntology":null},{"paper":null,"slug":"cameleval-advancing-culturally-aligned-arabic","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","date":"2024-09-19","arxiv_id":"2409.12623","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-product","title":"Exploring Large Language Models for Product Attribute Value Identification","date":"2024-09-19","arxiv_id":"2409.12695","n_code_links":0,"syntology":null},{"paper":"/paper/a-comprehensive-evaluation-of-quantized","slug":"a-comprehensive-evaluation-of-quantized","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","date":"2024-09-17","arxiv_id":"2409.11055","n_code_links":1,"syntology":null},{"paper":null,"slug":"challenging-fairness-a-comprehensive","title":"Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness","date":"2024-09-17","arxiv_id":"2409.10825","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-mental-health-support-through-human","title":"Enhancing Mental Health Support through Human-AI Collaboration: Toward Secure and Empathetic AI-enabled chatbots","date":"2024-09-17","arxiv_id":"2410.02783","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-and-enhancing-trustworthiness-of","slug":"measuring-and-enhancing-trustworthiness-of","title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","date":"2024-09-17","arxiv_id":"2409.11242","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["declare-lab/trust-align"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nvlm-open-frontier-class-multimodal-llms","title":"NVLM: Open Frontier-Class Multimodal LLMs","date":"2024-09-17","arxiv_id":"2409.11402","n_code_links":0,"syntology":null},{"paper":"/paper/improving-multi-candidate-speculative","slug":"improving-multi-candidate-speculative","title":"Improving Multi-candidate Speculative Decoding","date":"2024-09-16","arxiv_id":"2409.10644","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["JackZeng0208/DynaSD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"kodexv0-1-a-family-of-state-of-the-art","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","date":"2024-09-13","arxiv_id":"2409.13749","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimenting-with-legal-ai-solutions-the","title":"Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice","date":"2024-09-12","arxiv_id":"2409.07713","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-large-language-models-for-entity","slug":"fine-tuning-large-language-models-for-entity","title":"Fine-tuning Large Language Models for Entity Matching","date":"2024-09-12","arxiv_id":"2409.08185","n_code_links":1,"syntology":null},{"paper":null,"slug":"theragen-therapy-for-every-generation","title":"TheraGen: Therapy for Every Generation","date":"2024-09-12","arxiv_id":"2409.13748","n_code_links":0,"syntology":null},{"paper":"/paper/llm-based-feature-generation-from-text-for","slug":"llm-based-feature-generation-from-text-for","title":"LLM-based feature generation from text for interpretable machine learning","date":"2024-09-11","arxiv_id":"2409.07132","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-large-language-model-pretraining","title":"Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review","date":"2024-09-10","arxiv_id":"2409.06131","n_code_links":0,"syntology":null},{"paper":null,"slug":"elsevier-arena-human-evaluation-of-chemistry","title":"Elsevier Arena: Human Evaluation of Chemistry/Biology/Health Foundational Large Language Models","date":"2024-09-09","arxiv_id":"2409.05486","n_code_links":0,"syntology":null},{"paper":null,"slug":"regression-with-large-language-models-for","title":"Regression with Large Language Models for Materials and Molecular Property Prediction","date":"2024-09-09","arxiv_id":"2409.06080","n_code_links":0,"syntology":null},{"paper":"/paper/vision-fused-attack-advancing-aggressive-and","slug":"vision-fused-attack-advancing-aggressive-and","title":"Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation","date":"2024-09-08","arxiv_id":"2409.05021","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["levelower/vfa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"can-opensource-beat-chatgpt-a-comparative","title":"Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation","date":"2024-09-06","arxiv_id":"2409.04164","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-large-language-models-for-domain-1","slug":"fine-tuning-large-language-models-for-domain-1","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","date":"2024-09-05","arxiv_id":"2409.03444","n_code_links":7,"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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lamm-mit/llm-finetuning"],"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":"how-much-data-is-enough-data-fine-tuning","title":"How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes","date":"2024-09-05","arxiv_id":"2409.03454","n_code_links":0,"syntology":null},{"paper":null,"slug":"occllama-an-occupancy-language-action","title":"OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving","date":"2024-09-05","arxiv_id":"2409.03272","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-cyber-incident-timeline-analysis","title":"GenDFIR: Advancing Cyber Incident Timeline Analysis Through Retrieval Augmented Generation and Large Language Models","date":"2024-09-04","arxiv_id":"2409.02572","n_code_links":0,"syntology":null},{"paper":"/paper/more-is-more-addition-bias-in-large-language","slug":"more-is-more-addition-bias-in-large-language","title":"More is More: Addition Bias in Large Language Models","date":"2024-09-04","arxiv_id":"2409.02569","n_code_links":1,"syntology":null},{"paper":null,"slug":"smileyllama-modifying-large-language-models","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","date":"2024-09-03","arxiv_id":"2409.02231","n_code_links":0,"syntology":null}],"record_sha256":"46224c2f554d6e7c7fb2dc0a75384dd1b8c998e981004baa515834d604b4cb4d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}