Hard-attention Transformers with W parameters and depth L have VC dimension Θ(WL log(TW)); teacher forcing is sample-optimal for chain-of-thought learning.
mega hub Canonical reference
LLaMA: Open and Efficient Foundation Language Models
Canonical reference. 82% of citing Pith papers cite this work as background.
1329
Pith papers citing it
3,905
external citations · Pith
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 207
method 20
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
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.
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.
RoPE frequency usage is determined by a data-induced dependency width W, with the optimal frequency scaling as π/W, explaining both learned spectra and the success of position interpolation.
Linear NCDEs replace non-linear vector fields with linear ones, enabling parallel-in-time training via associative scans while retaining maximal theoretical expressivity and achieving state-of-the-art time series performance at up to 1000x speedup.
HERMES provides a reusable hierarchical labeling substrate for pre-training data that reveals granularity-specific effects in data mixing rules during model training.
OntoLearner supplies the first cross-domain ontology collection and benchmarking infrastructure for LLM-driven ontology learning, finding that failure scales with ontological complexity instead of model size.
citing papers explorer
-
Tight Sample Complexity of Transformers
Hard-attention Transformers with W parameters and depth L have VC dimension Θ(WL log(TW)); teacher forcing is sample-optimal for chain-of-thought learning.
-
SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models
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.
-
Privacy Auditing with Zero (0) Training Run
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.
-
Effective Context in Transformers: An Analysis of Fragmentation and Tokenization
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.
-
Grid Games: The Power of Multiple Grids for Quantizing Large Language Models
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.
-
Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
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.
-
When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
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.
-
Backdoor Attacks on Decentralised Post-Training
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.
-
Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
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: An Enterprise Benchmark for Text-to-SQL
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: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
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: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
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: a multimodal agent benchmark to evaluate AI in simulated clinical environments
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: Monolithic Preference Optimization without Reference Model
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.
-
Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
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: Linear-Time Sequence Modeling with Selective State Spaces
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: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
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: Deliberate Problem Solving with Large Language Models
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: A Comprehensive Benchmark for Tool-Augmented LLMs
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.
-
Instruction Tuning with GPT-4
GPT-4-generated instruction data produces superior zero-shot performance in finetuned LLaMA models versus prior state-of-the-art data.
-
How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization
RoPE frequency usage is determined by a data-induced dependency width W, with the optimal frequency scaling as π/W, explaining both learned spectra and the success of position interpolation.
-
Advances in Neural Controlled Differential Equations
Linear NCDEs replace non-linear vector fields with linear ones, enabling parallel-in-time training via associative scans while retaining maximal theoretical expressivity and achieving state-of-the-art time series performance at up to 1000x speedup.
-
HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures
HERMES provides a reusable hierarchical labeling substrate for pre-training data that reveals granularity-specific effects in data mixing rules during model training.
-
OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models
OntoLearner supplies the first cross-domain ontology collection and benchmarking infrastructure for LLM-driven ontology learning, finding that failure scales with ontological complexity instead of model size.
-
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
Multi-agent LLMs classify USPTO reactions and write verified SMIRKS rules, expanding a reaction taxonomy from 68 to 14,073 classes and matching proprietary classifiers on held-out and out-of-distribution data.
-
Probing Memorization of Tabular In-Context Learning
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.
-
A Sensitivity-Aware Test Collection for Search Among Personal Information
A new sensitivity-labeled test collection is released from Enron emails with crowdsourced queries, relevance judgments, and LLM extensions for evaluating sensitivity-aware search.
-
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
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.
-
An Empirical Study of LLM-Generated Specifications for VeriFast
LLMs preserve functional behavior in over 91% of generated VeriFast specifications and source code but achieve only 31.4% verification success, with 94% of failures due to separation logic domain knowledge errors.
-
In-Context World Modeling for Robotic Control
Prepending a few self-generated random interaction clips as context lets VLA policies identify novel camera viewpoints and morphologies at test time and outperform multi-view baselines without parameter updates.
-
$\text{DT}^2$: Decision-Targeted Digital Twins
DT² trains digital twins to preserve pairwise policy rankings from fitted Q-evaluation on offline data rather than minimizing one-step transition errors, improving policy ranking and reducing decision regret.
-
SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity
SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
-
The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order
Lie brackets of gradient fields provide a geometric score for optimal transfer order in sequential learning, enabling efficient ranking of many sources via tournament methods.
-
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL introduces a learnable specification language for sewing patterns that lets vision-language models reconstruct explicit, simulation-ready 3D garments from single images, backed by a new 300K paired dataset.
-
MeshFlow: Mesh Generation with Equivariant Flow Matching
MeshFlow applies equivariant optimal-transport flow matching to generate triangle meshes as soups, matching autoregressive quality with an 18x inference speedup.
-
Convergence of Gradient Descent for General Neural Network Architectures Beyond the NTK Regime
Proves GD convergence to stationary point neighborhoods for general NN architectures beyond NTK via block-level analysis, analyticity, and local smoothness conditions.
-
Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models
Entity-level membership inference determines whether information about a target real-world entity was used in LLM training, using only black-box generated text and achieving AUC up to 0.97 on person entities.
-
UniRank: Unified Rank Allocation for Low-Rank LLM Compression
UniRank introduces dual local-global scoring for rank allocation in LLM low-rank decomposition plus rank-preserving fine-tuning, achieving up to 50% lower perplexity than uniform baselines in one-shot compression.
-
GitReq: A Gold Standard Dataset for Software Quality Requirements
GitReq is a released dataset of 6,302 expert-labeled GitHub requirements across eight ISO 25010 categories with LLM classification baselines.
-
Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective
Muon moves faster along signal river directions early but converges slower or oscillates near optima than GD due to orthogonal updates removing scale information, supporting two-stage optimization.
-
Triage Score: A Counterfactual Risk Assessment Instrument
Triage scores extend risk scores via additive counterfactual utilities to incorporate intervention effects in high-stakes decisions.
-
Shifting-based Optimizable Linear Relaxations for General Activation Functions
SLiR parameterizes linear relaxations by slope and uses shifting to compute sound bounds for general activation functions, enabling up to 7.8x more verified properties than prior methods.
-
RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models
RTSGameBench is a new extensible benchmark for VLMs using diverse RTS matchups, diagnostic mini-games targeting individual competencies, and a self-evolving query-to-game generator, with results showing poor VLM performance on tight coordination and large-scale tasks.
-
SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
SAGE is a source-agnostic post-hoc correction for LLM unlearning updates that suppresses components aligned with high-energy retained activation directions while preserving the forgetting carrier.
-
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
-
How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural
Linear recoverability of transformer FFN blocks varies widely across depth, is learned during training, and is independent of the activation function.
-
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
LongSpike integrates fractional-order state-space modeling into spiking neural networks, enabling better long-sequence performance than prior SNNs on LRA, WikiText-103, and Speech Commands benchmarks while retaining sparse computation.
-
Representing Time Series as Structured Programs for LLM Reasoning
T2SP converts time series into structured programs for trends, periods, and events, enabling off-the-shelf LLMs to perform better on editing, captioning, and QA tasks than raw string inputs.
-
Boltzmann Attention: Learnable Ising Couplings for Cooperative Attention
Boltzmann attention augments query-key attention with learnable Ising pairwise couplings, yielding consistent gains over softmax attention on character language modeling and bracket matching that increase with sequence length.
-
Quo Vadis, Visual In-Context Learning? A Unified Benchmark Across Domains and Tasks
The paper constructs the VIBE benchmark and evaluates six visual in-context learning models on 14 datasets, 12 tasks, and 106 combinations under a unified one-shot protocol, revealing limitations and failure modes.