Depth-L transformers with W parameters have VC dimension Theta(L W log(T W)), yielding matching O(L W log((T+T')W)) upper and Omega(L W log((T+T')W/L)) lower bounds on sample complexity for chain-of-thought learning.
super hub Canonical reference
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Canonical reference. 73% of citing Pith papers cite this work as background.
175
Pith papers citing it
Background
73% of classified citations
abstract
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. The latest model developed by OpenAI, GPT-4, was trained using an unprecedented scale of compute and data. In this paper, we report on our investigation of an early version of GPT-4, when it was still in active development by OpenAI. We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models. We discuss the rising capabilities and implications of these models. We demonstrate that, beyond its mastery of language, GPT-4 can solve novel and difficult tasks that span mathematics, coding, vision, medicine, law, psychology and more, without needing any special prompting. Moreover, in all of these tasks, GPT-4's performance is strikingly close to human-level performance, and often vastly surpasses prior models such as ChatGPT. Given the breadth and depth of GPT-4's capabilities, we believe that it could reasonably be viewed as an early (yet still incomplete) version of an artificial general intelligence (AGI) system. In our exploration of GPT-4, we put special emphasis on discovering its limitations, and we discuss the challenges ahead for advancing towards deeper and more comprehensive versions of AGI, including the possible need for pursuing a new paradigm that moves beyond next-word prediction. We conclude with reflections on societal influences of the recent technological leap and future research directions.
hub tools
citation-role summary
background 35
method 4
baseline 1
dataset 1
citation-polarity summary
claims ledger
- abstract Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. The latest model developed by OpenAI, GPT-4, was trained using an unprecedented scale of compute and data. In this paper, we report on our investigation of an early version of GPT-4, when it was still in active development by OpenAI. We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example)
authors
co-cited works
representative citing papers
Only two of seven LLMs produce positive returns on live Polymarket data, with MiMo-V2-Flash at 17.6% CWR and Gemini-3-Flash at 6.2% CWR while the other five lose money.
LiveBench is a contamination-limited LLM benchmark with auto-scored challenging tasks from recent sources across math, coding, reasoning and more, where top models score below 70%.
RepairAgent autonomously repairs 164 bugs on Defects4J including 39 not fixed by prior techniques by treating an LLM as an agent that invokes tools via a finite state machine and dynamic prompts.
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.
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
Tiny language models under 10M parameters trained on a synthetic children's story dataset generate fluent, consistent, multi-paragraph English text with near-perfect grammar and reasoning.
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.
Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
LLMs score 84.9% on genuine riddles but 50.7% on riddle riddles requiring literal answers, opposite to humans (50.5% vs 80.5%), indicating memory retrieval over flexible strategy selection.
CrypFormBench is a new benchmark jointly covering symbolic and computational security to evaluate LLMs on five formal analysis capabilities, with results showing top model Claude-3.5 scores 48.7/100 and most models struggling on generation, transformation, and correction.
HALO distills VLM priors via question-answering objectives and applies sparse attention to enable reliable memory retrieval from up to eight minutes of history in imitation-learned visuomotor policies.
Introduces DAF-AGI, a second-order conceptual artifact with ordinal criteria for AGI definition fitness and a structured governance audit, demonstrated on five measurement families and tested against a generative-systems arrival claim.
Introduces TBPO, which derives a Bregman-divergence density-ratio matching objective for token-level preference optimization that generalizes DPO while preserving the induced optimal policy.
SMC forgets its initial condition geometrically in the jump chain and as 1/ℓ in continuous genetic distance, justifying independent-locus approximations.
ROSE is a retrieval-augmented plug-in that improves MLLM segmentation on novel and emerging entities by fetching web text and images and deciding when to use them.
LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.
CrossTraffic encodes transportation methodologies in an executable core and ontology-driven knowledge graph, enabling LLM-assisted analyses with near-zero numerical error and perfect invalid-input detection.
Stronger LLMs show near-perfect physical reasoning in circuits but violate explicit sign and polarity instructions in trap setups, while weaker models follow instructions better but reason less accurately.
SLIP enables self-jailbreaking of aligned LLMs via lexical insertion in breadth-first tree search, reaching 94.7% average ASR on AdvBench and HarmBench across eleven models with ~7.9 calls.
TSVer is a new benchmark dataset for fact verification against time-series evidence, with 304 annotated real-world claims, 400 time series, verdicts, and justifications, plus baseline results showing current models struggle.
LLMs achieve 81% coherent execution simulation on HumanEval but show mostly random or weak consistency across tests, with frontier models relying on natural language shortcuts instead of true program analysis.
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.
This survey provides the first comprehensive overview of deep multimodal learning methods designed to remain robust when some input modalities are absent.
citing papers explorer
-
Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs
Helicase proposes an autonomous multi-agent LLM framework for uncertainty-guided supply chain knowledge graph construction evaluated on the new SCQA benchmark of 80 queries.
-
Repeated Sequences Reveal Gaps between Large Language Models and Natural Language
Natural language shows stable entropy-growth patterns in repeated subsequences while GPT texts exhibit systematic shifts in exponents with model size.
-
Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
LINK improves cross-lingual knowledge transfer via lexical substitutions in English pretraining data, yielding notable downstream gains and up to 2x training speedup across eight languages and five model sizes.
-
Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
Robots detect underspecified reward features via demonstration variation and query targeted natural language explanations to improve reward recovery from imperfect demos.
-
Faster Completion, Less Learning: Generative AI Reduced Study Time on Math Problems and the Knowledge They Build
Generative AI reduced study time on AI-susceptible math problems by 9-31% across grade levels and produced a 25% decline in retention odds on proctored assessments.
-
Task Abstention for Large Language Models in Code Generation
A distribution-free abstention rule grounded in multiple hypothesis testing uses execution consistency to let code LLMs avoid hallucination-prone tasks with theoretical guarantees.
-
LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling
LPDS quantifies difficulty of logic-preserving problem variations and searches for the hardest ones, producing up to 5x larger performance drops than random sampling and better robustness gains from fine-tuning on difficult examples.
-
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.
-
CHAL: Council of Hierarchical Agentic Language
CHAL is a multi-agent dialectic system that performs structured belief optimization over defeasible domains using Bayesian-inspired graph representations and configurable meta-cognitive value system hyperparameters.
-
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
-
Making Abstraction Concrete: A Design Space and Interaction Model of Abstraction in Interactive Systems
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
-
When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews
Introduces RevCI benchmark and IMPACT multi-agent framework for evidence-level contradiction detection and graded intensity scoring in peer reviews, distilled into efficient TIDE model.
-
FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution
FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
Process Matters more than Output for Distinguishing Humans from Machines
A new battery of 30 cognitive tasks demonstrates that process-level behavioral features distinguish humans from frontier AI agents better than performance metrics (mean AUC 0.88), with process-specific fine-tuning improving mimicry but limited cross-task transfer.
-
DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis
DSIPA is a zero-shot black-box detector that uses sentiment distribution consistency and preservation metrics to identify LLM text, reporting up to 49.89% F1 gains over baselines across domains and models.
-
R$^3$AG: Retriever Routing for Retrieval-Augmented Generation
R³AG routes queries to retrievers by decomposing capabilities into retrieval quality and generation utility, trained via contrastive learning on document assessments and downstream answer correctness to outperform static methods.
-
River-LLM: Large Language Model Seamless Exit Based on KV Share
River-LLM enables token-level early exit in decoder-only LLMs by routing exited tokens through 4-bit quantized copies of backbone layers that share the KV cache addressing scheme, achieving 1.53–2.16× wall-clock speedup without training.
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents
Persistent memory is necessary and sufficient for LLM poker agents to reach ToM levels 3-5 and use strategic deception, while agents without memory stay at level 0.
-
Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News
Humans cannot reliably distinguish LLM-generated news from human-written news across multiple models, with domain expertise providing only modest help and fatigue reducing accuracy over time.
-
Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
GR3D turns 3D scene geometry into ID-indexed text references, enabling zero-shot MLLM spatial reasoning gains of 9% on VSI-Bench and 12% on MindCube.
-
Identification of quantum generative circuits with parallel quantum neural network
ParaQuanNet distinguishes eight quantum generative circuits via 99.5% accurate classification of their output data using parallel quantum embeddings and mutually unbiased measurements.
-
Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
LLMs dynamically construct and causally rely on structured conceptual subspaces in middle-to-late layers for in-context inference.
-
Large Language Models as Students Who Think Aloud: Overly Coherent, Verbose, and Confident
LLMs simulating student think-alouds in multi-step chemistry tutoring produce overly coherent, verbose, and confident reasoning that overestimates learner success compared to 630 human utterances.
-
Large Language Models have Chain-of-Affect
LLMs exhibit structured chain-of-affect dynamics with stable family fingerprints, convergence to accumulation-overload-numbing under negative exposure, and downstream effects on generation, human interaction, and group polarization.
-
AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.
-
Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models
A Bayesian framework disentangles topic, agreement, and anchoring biases from interaction effects in LLM multi-turn dialogues, revealing convergence to attractors that shift with fine-tuning.
-
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
-
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
BTC-LLM uses a binary codebook for pattern clustering and a learnable transformation to achieve 0.7-1.11 bit LLM quantization while limiting accuracy loss to a few percent on LLaMA and Qwen models.
-
When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Presents YesBut (V2) benchmark and shows state-of-the-art VLMs significantly underperform humans on tasks requiring comparative reasoning for contradictory humor in comics.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-world booking scenarios.
-
RouteLLM: Learning to Route LLMs with Preference Data
Router models trained on preference data dynamically select between strong and weak LLMs, cutting inference costs by more than 2x on benchmarks with no quality loss and showing transfer to new model pairs.
-
Argumentative Large Language Models for Explainable and Contestable Claim Verification
ArgLLMs build argumentation frameworks from LLMs to support explainable and contestable formal reasoning for claim verification.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
-
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.
-
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
-
SGLang: Efficient Execution of Structured Language Model Programs
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.
-
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
ToRA trains language models on interactive tool-use trajectories with imitation learning and output shaping to integrate reasoning and external tools, yielding 13-19% gains on math datasets and new highs like 44.6% on MATH for a 7B model.
-
Ragas: Automated Evaluation of Retrieval Augmented Generation
Ragas supplies reference-free metrics for measuring context relevance, faithfulness to retrieved passages, and answer quality in RAG pipelines.
-
Language Modeling Is Compression
Large language models serve as strong general-purpose lossless compressors for text, images, and audio, outperforming domain-specific methods and revealing insights into scaling, tokenization, and in-context learning.
-
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
GPTFuzz is a black-box fuzzing framework that mutates seed jailbreak templates to automatically generate effective attacks, achieving over 90% success rates on models including ChatGPT and Llama-2.
-
Textbooks Are All You Need II: phi-1.5 technical report
phi-1.5 is a 1.3B parameter model trained on synthetic textbook data that matches the reasoning performance of models five times larger on natural language, math, and basic coding tasks.
-
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
WizardMath applies RLEIF to produce open-source LLMs that reach new state-of-the-art math reasoning scores on GSM8k and MATH, with the 70B variant surpassing GPT-3.5-Turbo, Claude 2, Gemini Pro, and early GPT-4.
-
Reinforced Self-Training (ReST) for Language Modeling
ReST improves LLM translation quality on benchmarks via offline RL on self-generated data, achieving gains in a compute-efficient way compared to typical RLHF.
-
Textbooks Are All You Need
A 1.3B-parameter code model trained on 7B tokens of curated textbook and synthetic data achieves 50.6% on HumanEval, indicating data quality can enable strong performance at small scale.
-
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
GPT-4 as an LLM judge achieves over 80% agreement with human preferences on MT-Bench and Chatbot Arena, matching human agreement levels and providing a scalable evaluation method.
-
Gorilla: Large Language Model Connected with Massive APIs
Gorilla is a fine-tuned LLM that surpasses GPT-4 in accurate API call generation and uses retrieval to handle documentation updates.