SVHalluc benchmark shows open-source audio-visual LLMs achieve near-random accuracy on semantic and temporal speech-vision alignment tasks while Gemini 2.5 Pro performs substantially better.
mega hub Canonical reference
LLaMA: Open and Efficient Foundation Language Models
Canonical reference. 82% of citing Pith papers cite this work as background.
1144
Pith papers citing it
Background
82% of classified citations
abstract
We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.
hub tools
citation-role summary
background 206
method 19
baseline 8
other 6
dataset 1
extension 1
citation-polarity summary
claims ledger
- abstract We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
Zero-Run auditing supplies valid lower bounds on differential privacy parameters from fixed member and non-member datasets by modeling and correcting distribution-shift confounding via causal-inference techniques.
Fragmentation strictly raises optimal finite-context log-loss on Markov sources while tokenization can make a short token window equivalent to a longer source window under reliability and compression conditions.
Allowing each quantization group to select among multiple 4-bit grids improves accuracy over single-grid FP4 for both post-training and pre-training of LLMs.
Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.
An adversary controlling an intermediate pipeline stage in decentralized LLM post-training can inject a backdoor that reduces alignment from 80% to 6%, with the backdoor persisting in 60% of cases even after subsequent safety training.
First study of 1,899 MCP servers finds eight distinct vulnerabilities (only three traditional), 7.2% with general issues, 5.5% with tool poisoning, and 66% with code smells, urging MCP-specific security practices.
BEAVER is the first text-to-SQL benchmark from private enterprise data warehouses, revealing SOTA agentic frameworks achieve only 10.8% accuracy on complex real-world queries.
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.
AgentClinic is a multimodal agent benchmark demonstrating that LLM diagnostic accuracy on MedQA drops to below one-tenth in sequential clinical simulations, with Claude-3.5 leading and large tool-use differences across models.
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
BLaIR is a new benchmark and 570M-review dataset showing that LLM performance rankings on recommendation tasks have little correlation with rankings on general embedding benchmarks like MTEB.
Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.
MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.
API-Bank is a new benchmark and training dataset for tool-augmented LLMs that shows fine-tuned models can approach GPT-3.5 tool-use effectiveness.
GPT-4-generated instruction data produces superior zero-shot performance in finetuned LLaMA models versus prior state-of-the-art data.
LA-SR redefines unpaired super-resolution in language space by projecting images into a semantically rich representation and applying vision-language model guided losses to handle real-world degradations extracted from depth variations.
A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under realistic training.
DynaSteer dynamically steers LLM reasoning trajectories toward truth via pattern clustering, Fisher-LDA projection, and entropy-triggered representation edits, improving performance on MATH and generalizing to coding.
A new sensitivity-labeled test collection is released from Enron emails with crowdsourced queries, relevance judgments, and LLM extensions for evaluating sensitivity-aware search.
LaViD distills LLM conceptual knowledge to vision models via LLM-generated MCQ soft labels, outperforming vision-language distillation baselines on fine-grained benchmarks while improving robustness on spurious correlation datasets.
citing papers explorer
-
A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions
A synthesis of 30 secondary studies finds strong benchmark accuracy for LLM code generation but weak real-world generalization, fragile robustness, pervasive efficiency issues, and under-reported bias, calling for domain-aware improvements and standardized evaluation.
-
Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
A training-free region-aware attention recalibration strategy reduces object hallucinations in LVLMs on CHAIR, POPE, and MME benchmarks while preserving fluency.
-
The New Associationism: Lessons from Deep Learning
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
-
m3BERT: A Modern, Multi-lingual, Matryoshka Bidirectional Encoder
m3BERT uses a three-stage Matryoshka pretraining approach on a bidirectional encoder to support variable embedding sizes while outperforming prior models on large-scale retrieval tasks.
-
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
SynGR is a new framework for generative recommendation that constrains overreliance on single modalities to exploit synergistic cross-modal information for better item semantics and user preference modeling.
-
From Detection to Response: A Deep Learning and Retrieval-Augmented Generation Framework for Network Intrusion Mitigation
Ensemble of three binary DNNs classifies network flows as benign, DoS or DDoS at 99.84% and 95.30% accuracy on CICIDS2018 and UNSW-NB15, paired with RAG to generate mitigation reports that outperform vanilla LLM outputs.
-
DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
DuIVRS-2 deploys an LLM-driven IVR pipeline that processes 0.4 million calls per day at 83.9 percent task success rate using FSM-guided augmentation, selective CoT generation, and cooperative policy iteration.
-
Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation
Static checking rewards and moderate AST-based hints improve diffusion RL performance for code generation, with effectiveness varying by task difficulty across HumanEval, MBPP, and LiveCodeBench.
-
Toward LLMs Beyond English-Centric Development
Analysis of open-weight LLMs reveals strong English bias in generated sequences, with continual pre-training providing no cost benefit over from-scratch training for non-English adaptation.
-
UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars
UMo presents a sparse MoE-based unified model for real-time co-speech avatar animation that claims superior quality under latency constraints via keyframe-centric design and multi-stage audio-augmented training.
-
Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation
Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.
-
Transformer Interpretability from Perspective of Attention and Gradient
A gradient-guiding technique for Transformer attention interpretation yields detailed feature maps and reveals imperceptible image class-rewriting attacks on Vision Transformers.
-
HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support
HPC-LLM fine-tunes Llama 3.1 8B via QLoRA on 9k-24k HPC examples and adds dense retrieval to deliver practical support for job scheduling, MPI, and GPU workflows, approaching the performance of larger general models at lower memory and latency cost.
-
Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.
-
Gyan: An Explainable Neuro-Symbolic Language Model
Gyan is a novel explainable non-transformer language model that achieves SOTA results on multiple datasets by mimicking human-like compositional context and world models.
-
Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer
Nora is a matrix optimizer that stabilizes weight norms and angular velocities through row-wise momentum projection onto the orthogonal complement of the weights while approximating structured preconditioning with O(mn) complexity and proven scalability.
-
RLDX-1 Technical Report
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.
-
HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs
HalluScan benchmark evaluates hallucination detection in LLMs, reporting NLI Verification at AUROC 0.88 and introducing HalluScore (r=0.41 with humans) plus Adaptive Detection Routing for 2x cost savings.
-
Cross-Layer Energy Analysis of Multimodal Training on Grace Hopper Superchips
On Grace Hopper superchips, energy efficiency during multimodal training is governed by data movement and overlap rather than compute utilization, and runtime-optimal configurations are not always energy-optimal.
-
RETO: A Rotary-Enhanced Transformer Operator for High-Fidelity Prediction of Automotive Aerodynamics
RETO achieves relative L2 errors of 0.063 on ShapeNet and 0.089/0.097 on DrivAerML surface pressure/velocity, outperforming Transolver and other baselines.
-
Automated Detection of Mutual Gaze and Joint Attention in Dual-Camera Settings via Dual-Stream Transformers
A dual-stream Transformer using frozen GazeLLE backbones and custom token fusion detects mutual gaze and joint attention from dual-camera recordings, outperforming CNN baselines and a multimodal LLM on caregiver-infant data.
-
An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code
Locally deployed LLMs achieve 43-45% accuracy on Python bug detection but frequently produce only partial identifications of problematic code regions.
-
Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs
A dynamic data valuation system for LLMs combines token entropy, influence functions, and proxy-based Shapley estimates to price data by its measured contribution to model performance, outperforming simple count-based methods in experiments across instruction, math, and code tasks.
-
A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies
Human-AI coexistence is best modeled as conditional mutualism under governance, formalized as a multiplex dynamical system whose simulations show stable high-coexistence equilibria only under balanced institutional oversight.
-
TabSHAP
TabSHAP attributes feature impact in LLM tabular classifiers via sampled Shapley coalitions and JSD on output distributions, reporting higher deletion faithfulness than random or XGBoost-proxy baselines on Adult Income and Heart Disease data.
-
Leveraging Multimodal LLMs for Built Environment and Housing Attribute Assessment from Street-View Imagery
Fine-tuning Gemma 3 27B on modest human-labeled street-view data yields building condition scores that align with and sometimes exceed individual human raters on correlation metrics, with knowledge distillation producing comparable smaller LLM, CNN, and transformer models.
-
Effects of Cross-lingual Evidence in Multilingual Medical Question Answering
Combining English and target-language web retrieval boosts medical QA for low-resource languages to match high-resource performance, while English web data benefits high-resource languages most and specialized sources like PubMed lack multilingual coverage.
-
Investigating Conversational Agents to Support Secondary School Students Learning CSP
A classroom evaluation with 45 high school students finds that conversational agents can aid CSP learning by delivering context-appropriate information, comparing general and custom agent approaches for effectiveness and engagement.
-
The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings
Advanced LLMs improve EFL writing scores and diversity for lower-proficiency students but correlate with lower expert ratings on deep coherence, acting more as crutches than scaffolds.
-
In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions
Lightweight training strategies allow speech-aware LLMs to output accurate word timestamps alongside ASR transcripts while also improving recognition quality across datasets.
-
Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores
AILFM uses active imitation learning to learn thermal- and kernel-aware scheduling policies for LFM inference on 3D S-NUCA many-cores, outperforming baselines while maintaining thermal safety.
-
A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
Dense retrieval plus query reformulation and reranking reaches 60.49% accuracy on MedQA USMLE, outperforming other setups while domain-specialized models make better use of the retrieved evidence.
-
An empirical study of LoRA-based fine-tuning of large language models for automated test case generation
LoRA fine-tuning enables open-source LLMs such as Ministral-8B to generate requirement-based test cases at a level comparable to pre-tuned proprietary GPT-4.1 models.
-
BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection
BiMind outperforms existing methods in incorrect information detection by disentangling content and knowledge reasoning with attention geometry adaptation and self-retrieval.
-
Cardinality Estimation for High Dimensional Similarity Queries with Adaptive Bucket Probing
An LSH-based system with adaptive bucket probing, progressive sampling, and product quantization estimates cardinality for high-dimensional similarity queries efficiently.
-
Combining Static Code Analysis and Large Language Models Improves Correctness and Performance of Algorithm Recognition
Hybrid LLM plus static analysis for algorithm recognition in code cuts required model calls by 72-97% and lifts F1-scores by as much as 12 points.
-
Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning
RAG-adapted LLaMA-3-8B outperforms both baseline and fine-tuned models on expert-rated accuracy (75.5%), relevance (90.8%), and overall preference (85.2%) for additive manufacturing questions.
-
DFLOP: A Data-driven Framework for Multimodal LLM Training Pipeline Optimization
DFLOP is a data-driven framework that profiles data-induced computation variance and uses predictive scheduling to balance workloads in multimodal LLM training pipelines, claiming up to 3.6x faster training than existing frameworks.
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
-
Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval
Large-scale profiling of recent AI literature shows growth in safety, multimodal reasoning, and agent studies alongside stabilization in neural machine translation and graph methods.
-
AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control
AdaFRUGAL automates FRUGAL's static hyperparameters with linear decay on subspace ratio and loss-aware update frequency, delivering competitive accuracy with lower memory and faster training on C4, VietVault, and GLUE.
-
Predicting one-year clinical instability and mortality in heart failure patients using sequence modeling
Sequence models on EHR data from a Swedish heart failure cohort achieve AUPRCs of 0.555 to 0.854 for one-year instability and mortality predictions and support four care pathways.
-
Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid
G-TRACE provides region-aware estimates of GenAI carbon emissions including 4309 MWh and 2068 tCO2 for a 2024-2025 image generation trend, paired with a seven-level AI Sustainability Pyramid for policy guidance.
-
Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++
LLMs perform well on basic syntactic and semantic bugs in small code but struggle with complex security vulnerabilities and large production codebases.
-
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
GLM-4.5, a 355B-parameter MoE model with hybrid reasoning, scores 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified while ranking 3rd overall and 2nd on agentic benchmarks.
-
Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design
A fine-tuned LLM called Perovskite-R1, built from curated perovskite literature and material libraries, proposes precursor additives and designs with some experimental validation showing improved stability and performance.
-
Show-o2: Improved Native Unified Multimodal Models
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.
-
Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection
An LLM-assisted annotation pipeline creates the PodSarc sarcastic speech dataset from podcasts and validates it via a collaborative gating detection model reaching 73.63% F1.
-
Responsible Federated LLMs via Safety Filtering and Constitutional AI
Integrates safety filtering and constitutional AI into FedLLM, reporting over 20% safety improvement on AdvBench.
-
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.