Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
super hub Canonical reference
Emergent Abilities of Large Language Models
Canonical reference. 86% of citing Pith papers cite this work as background.
126
Pith papers citing it
Background
86% of classified citations
abstract
Scaling up language models has been shown to predictably improve performance and sample efficiency on a wide range of downstream tasks. This paper instead discusses an unpredictable phenomenon that we refer to as emergent abilities of large language models. We consider an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models. The existence of such emergence implies that additional scaling could further expand the range of capabilities of language models.
hub tools
citation-role summary
background 33
baseline 2
citation-polarity summary
claims ledger
- abstract Scaling up language models has been shown to predictably improve performance and sample efficiency on a wide range of downstream tasks. This paper instead discusses an unpredictable phenomenon that we refer to as emergent abilities of large language models. We consider an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models. The existence of such emergence implies that additional scaling could further expand the range of capabilities of language model
authors
co-cited works
representative citing papers
Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
GPT-2 small solves indirect object identification via a circuit of 26 attention heads organized into seven functional classes discovered through causal interventions.
Token loss trajectories follow localized sigmoids whose learning-time spectrum quantitatively reconstructs scaling-law derivatives on T, D, and M axes and enables faster training via distribution reshaping.
Self-evolving rubric with anti-gaming fitness reveals that objective capability scaling fails to transfer to subjective LLM behaviors, with advice-restraint as the universal lowest dimension that can regress.
A multi-agent pipeline iteratively refines topology optimization outputs to match natural language preferences for branched structures, achieving 60% success rate across replicates in cantilever and phone-stand tasks.
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
Graphlets mined as structural tokens improve zero-shot inductive and transductive link prediction in knowledge graph foundation models across 51 diverse graphs.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
A 2D neural cellular automaton spontaneously self-organizes into a Proto-CKY representation that exhibits syntactic processing capabilities for context-free grammars when trained on membership problems.
PERCEIVE is the first bilingual benchmark integrating author content, reader emotions from comments, communication behavior, user attributes, and social graphs for personalized social media emotion understanding.
ATLAS is the first silicon-validated simulation framework for 3D-DRAM LLM accelerators, achieving under 8.57% error and over 97% correlation with real hardware while supporting design exploration.
LLM adoption in science follows a compressing inverted-U trajectory where release year predicts time-to-peak and lifespan better than model attributes.
Social dynamics in LLM collectives cause representative agents to make less accurate decisions as peer pressure increases through larger adversarial groups, more capable peers, longer arguments, and persuasive styles.
BoostTaxo introduces a boosting-style LLM framework for zero-shot taxonomy induction that uses hybrid candidate selection and constraint-aware calibration to achieve superior or comparable performance to prior methods on WordNet, DBLP, and SemEval-Sci benchmarks.
StackRepoQA shows LLMs reach only moderate accuracy on multi-file Java QA tasks, with gains from graph-based retrieval but frequent reliance on verbatim answer reproduction.
FactorEngine mines alpha factors as Turing-complete code via LLM-guided directional search, parameter separation, and a multi-agent pipeline that converts financial reports into executable programs, delivering higher IC/ICIR and Sharpe ratios than baselines in backtests.
Retrieval-augmented LLMs produce more cautious and guideline-aligned recommendations on cannabidiol for older adults than standalone models, demonstrated via automated evaluation on 64 diverse scenarios.
The ghost mechanism derives a 1D canonical model of abrupt learning in RNNs from ghost points of saddle-node bifurcations, predicting an inverse-power-law critical learning rate and gradient-based failure modes.
PolyMATH is a new 5,000-image benchmark where top MLLMs reach at most 41 percent accuracy on multi-modal mathematical reasoning, with ablation showing minimal gain from text over images.
Scaled vanilla autoregressive models based on Llama achieve 2.18 FID on ImageNet 256x256 image generation, beating popular diffusion models without visual inductive biases.
Introduces YesBut benchmark showing state-of-the-art multimodal models lag humans on interpreting humorous contradictions in comics.
DeepSeek-V2 delivers top-tier open-source LLM performance using only 21B active parameters by compressing the KV cache 93.3% and cutting training costs 42.5% via MLA and DeepSeekMoE.
GPT-4 LLM agents autonomously exploit 87% of tested one-day vulnerabilities when given CVE descriptions, far outperforming other models and tools.
citing papers explorer
-
Progress measures for grokking via mechanistic interpretability
Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
-
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
GPT-2 small solves indirect object identification via a circuit of 26 attention heads organized into seven functional classes discovered through causal interventions.
-
A ghost mechanism: An analytical model of abrupt learning in recurrent networks
The ghost mechanism derives a 1D canonical model of abrupt learning in RNNs from ghost points of saddle-node bifurcations, predicting an inverse-power-law critical learning rate and gradient-based failure modes.
-
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
WorkArena benchmark shows LLM web agents achieve partial success on enterprise tasks but have a substantial gap to full automation and perform worse with open-source models.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
Doubly robust estimators that incorporate low-rank predictions enable valid finite-sample confidence intervals for best-model identification under adaptive sampling and without-replacement example selection in LLM evaluation.
-
The Propagation Field: A Geometric Substrate Theory of Deep Learning
Neural networks possess a propagation field of trajectories and Jacobians whose quality can be measured and optimized independently of endpoint loss, yielding better unseen-path generalization and reduced forgetting in continual learning.
-
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
-
A Meta Reinforcement Learning Approach to Goals-Based Wealth Management
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
-
LLM-AUG: Robust Wireless Data Augmentation with In-Context Learning in Large Language Models
LLM-AUG applies LLM in-context learning for embedding-space data augmentation in wireless ML, outperforming baselines and reaching near-oracle accuracy with only 15% labeled data on RadioML and IC datasets.
-
Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
Transformers show limited adaptive depth use on relational reasoning, with clearer evidence after finetuning on the task.
-
Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
A conditional scaling law fitted on over 200 models from 80M to 3B parameters identifies architectures that deliver up to 2.1% higher accuracy and 42% higher inference throughput than LLaMA-3.2 under the same training budget.
-
Video models are zero-shot learners and reasoners
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
-
$\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
π₀ is a vision-language-action flow model trained on diverse multi-platform robot data that supports zero-shot task performance, language instruction following, and efficient fine-tuning for dexterous tasks.
-
Jailbroken: How Does LLM Safety Training Fail?
LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.
-
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
-
BloombergGPT: A Large Language Model for Finance
BloombergGPT is a 50B parameter LLM trained on a 708B token mixed financial and general dataset that outperforms prior models on financial benchmarks while preserving general LLM performance.
-
Large Language Models Are Human-Level Prompt Engineers
APE generates instruction candidates via LLM and selects the best by zero-shot performance of a second LLM, matching or beating human prompts on 19 of 24 NLP tasks.
-
In-Context Reward Adaptation for Robust Preference Modeling
Transformer model with response-time auxiliary input adapts reward models to unseen human preference domains via in-context learning from demonstrations.
-
Beyond Scaling: Agents Are Heading to the Edge
Personal agents require edge deployment to preserve high-fidelity local context and zero-latency loops, as claimed through three structural shifts away from cloud-centric designs.
-
Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
Experiments on modular arithmetic with heavy label noise show that over-parameterized networks form a distributed internal generalization structure that can be extracted via frequency methods to achieve high accuracy despite 80% noise.
-
Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models
Agentic AI systems are required to overcome the parameter coverage ceiling that prevents foundation models from handling certain out-of-distribution cases.
-
Optimized Deferral for Imbalanced Settings
MILD reformulates two-stage learning to defer as cost-sensitive learning over the input-expert domain and derives new margin-based losses with guarantees, yielding better performance than baselines on image classification and LLM routing tasks.
-
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.
-
Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs
GRPO tuning on SLMs shows diminishing returns from hard math samples, with easier subsets matching full performance using 45% fewer steps and GSM8K training outperforming MATH training on numeric subsets.
-
TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
-
CHESS: Contextual Harnessing for Efficient SQL Synthesis
CHESS deploys four LLM agents to retrieve information, prune schemas, generate refined SQL candidates, and validate via unit tests, reporting up to 71.10% accuracy on BIRD with 83% fewer calls than leading proprietary baselines.
-
At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization
Sparse autoencoders show OOD prompts increase fallacious concept activation in transformers, offering a mechanistic measure of shift and a path to robust fine-tuning.
-
LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems
A survey taxonomy of LLMs identifies three scaling crises and six efficiency paradigms while tracing the shift from generation to tool-using agents.
- The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models