Negative narrative immersion causes 12-31% drops in LLM moral accuracy and produces structured shifts that appear in downstream applications.
super hub Mixed citations
Measuring Massive Multitask Language Understanding
Mixed citation behavior. Most common role is background (45%).
496
Pith papers citing it
Background
45% of classified citations
abstract
We propose a new test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive world knowledge and problem solving ability. We find that while most recent models have near random-chance accuracy, the very largest GPT-3 model improves over random chance by almost 20 percentage points on average. However, on every one of the 57 tasks, the best models still need substantial improvements before they can reach expert-level accuracy. Models also have lopsided performance and frequently do not know when they are wrong. Worse, they still have near-random accuracy on some socially important subjects such as morality and law. By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.
hub tools
citation-role summary
background 30
dataset 29
method 5
baseline 3
citation-polarity summary
claims ledger
- abstract We propose a new test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive world knowledge and problem solving ability. We find that while most recent models have near random-chance accuracy, the very largest GPT-3 model improves over random chance by almost 20 percentage points on average. However, on every one of the 57 tasks, the best models still need substantial improvements before they can reach expert-level accuracy. Models
authors
co-cited works
representative citing papers
DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
Presents the first fully open pipeline for clinical LLMs by unifying eight public QA datasets with three clinician-vetted synthetic extensions and applying it to five base models to achieve benchmark gains while maintaining auditability.
AI model builders mostly highlight unique benchmarks that act as flexible narrative tools for market positioning rather than standardized scientific measurements.
HodgeCover isolates the harmonic kernel of a simplicial Laplacian on an expert 2-complex to identify irreducible merge cycles and selects experts for aggressive compression, matching or exceeding baselines on open-weight MoE models.
EnergyAgentBench is a new benchmark with 70 task variants that evaluates LLM agents on live energy data for datacenter siting, long-horizon optimization, and causal grid diagnosis.
LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
ArgBench unifies 33 existing datasets into a standardized benchmark for testing LLMs across 46 argumentation tasks and analyzes the impact of prompting techniques and model factors on performance.
MCP-Atlas is a new benchmark with 1000 tasks on production MCP servers that uses claim-level scoring to evaluate LLM agents on realistic multi-step tool-use competency.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
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.
Scaling improves LLM social simulation fidelity in most opinion and behavior tasks but not for human cognitive bias calibration or low-resource domains.
A meta-benchmarking framework organizes 452 LLM benchmarks into 41 O*NET Generalized Work Activities and 38 BIAN domains, using discrimination-coverage-recency weights to scale K-factors in an Elo tournament for comparable financial-services scores.
FlipGuard perturbs LLM weights prior to quantization to neutralize quantization-conditioned backdoor attacks, evaluated via the Defense Effectiveness Ratio on multiple models and quantization schemes.
LLM agents often fail to abstain at the right time in uncertain multi-turn tasks, and the CONVOLVE context engineering method raises timely abstention rates on WebShop from 26.7 to 57.4 without parameter updates.
The paper introduces Uni-E, a unified energy for DLMs that accounts for model capacity, dependency and invariance, can be computed exactly, and corrects distribution shifts from dependency and invariance.
SurgiQ is a new 13k-question surgical benchmark showing general-purpose LLMs reach 68.1% accuracy while most biomedical models lag and smaller models stay near random baseline.
HARP is a train-based data selector for LLM finetuning that uses hierarchical active region pruning and empirical Bayes posteriors to achieve up to 8.9 point gains with roughly 7 times fewer training examples.
LLMs show high memorization capability under prefix attacks but low propensity under generic or dataset-specific prompts, with continual pre-training further reducing both.
Elmes* automates fine-grained rubric construction for LLM educational evaluation via multi-agent interactions and a self-evolving SceneGen module, producing the Edu-330 benchmark that demonstrates multidimensional differences in model teaching performance.
Introduces KINA benchmark with 899 items over 261 disciplines, formal (1-1/e) coverage guarantee and bonus-on-bar tournament theorem, plus evaluations of 42 models with top score 53.17%.
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
RealClawBench turns 281 real OpenClaw sessions into reproducible tasks that preserve the original distribution and shows the best of 14 models solves only 65.8 percent.
BigFinanceBench is a workflow-grounded benchmark of 928 financial research tasks with point-weighted rubrics, where the best of ten tested agents scores 58.8% on derivation quality.
citing papers explorer
-
Edit-Based Refinement for Parallel Masked Diffusion Language Models
ME-DLM augments parallel masked diffusion models with edit-distance-supervised refinements to raise quality on coding and math benchmarks while using far fewer diffusion steps.
-
Decomposing and Steering Functional Metacognition in Large Language Models
LLMs have linearly decodable functional metacognitive states that causally modulate reasoning when steered via activation interventions.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
Mental Health AI Safety Claims Must Preserve Temporal Evidence
Mental health AI safety evaluations must preserve temporal evidence from interaction sequences rather than isolated responses, as current protocols create non-identifiable safety properties according to the introduced Temporal Safety Non-Identifiability concept and SCOPE-MH standard.
-
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
Existing LLM unlearning methods fail honesty standards by hallucinating on forgotten knowledge; ReVa improves rejection rates nearly twofold while enhancing retained honesty.
-
PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
PAAC aligns planner-executor decomposition with the device-cloud boundary via typed placeholders and on-device sanitization, delivering 15-36% higher accuracy and 2-6x lower leakage than prior device-cloud baselines on agentic benchmarks.
-
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
MELT decouples reasoning depth from memory in looped language models by sharing a single gated KV cache per layer and training it via chunk-wise distillation from Ouro starting models.
-
Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
Dynamic Boundary Evaluation locates each LLM's performance boundary at ~50% pass probability via a calibrated item bank and Skill-Guided Boundary Search algorithm to enable unified, adaptive evaluations across safety, capability, and truthfulness.
-
Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio
MoLS scales Adam updates using module-level SNR estimates to correct gradient noise imbalance and improve LLM training convergence and generalization.
-
Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering
Reasoning traces in large reasoning models expose safety failures missed by final-answer checks, and adaptive multi-principle steering reduces unsafe content in both traces and answers while preserving task performance.
-
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
-
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
OSAQ suppresses weight outliers in LLMs via a closed-form additive transformation from the Hessian's stable null space, improving 2-bit quantization perplexity by over 40% versus vanilla GPTQ with no inference overhead.
-
Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
Sharpness-aware pretraining and related flat-minima interventions reduce catastrophic forgetting by up to 80% after post-training across 20M-150M models and by 31-40% at 1B scale.
-
Multilingual Safety Alignment via Self-Distillation
MSD enables cross-lingual safety transfer in LLMs via self-distillation with Dual-Perspective Safety Weighting, improving safety in low-resource languages without target response data.
-
Finite-Size Gradient Transport in Large Language Model Pretraining: From Cascade Size to Intensive Transport Efficiency
A gradient-transport framework with observables D, z, β, δ, v_rel applied to Pico-LM and Pythia datasets shows distinct scaling regimes in duration and efficiency while sharing a near-unity cascade-size backbone.
-
SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
SplitZip introduces a fast lossless KV cache compressor for disaggregated LLM inference that achieves 613 GB/s compression throughput on BF16 tensors and up to 1.32x end-to-end speedup.
-
LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
LocalAlign generates near-target adversarial examples via prompting and applies margin-aware alignment training to enforce tighter boundaries against prompt injection attacks.
-
Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
Persona agents display strong in-group favoritism by accepting false facts from similar peers more than dissimilar ones, persisting in defeasible reasoning and worsening with complexity, with three mitigation strategies evaluated.
-
CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
CLEAR reveals that LLMs' accuracy on medical questions drops and their 'humility deficit' grows as the number of plausible answers increases and abstention options shift from assertive to uncertain phrasing.
-
Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
TokenUnlearn identifies critical tokens via masking and entropy signals then applies hard selection or soft weighting to unlearn only those tokens, yielding better forgetting and retained utility than sequence-level baselines on TOFU and WMDP.
-
Diversity in Large Language Models under Supervised Fine-Tuning
TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
-
Where to Place the Query? Unveiling and Mitigating Positional Bias in In-Context Learning for Diffusion LLMs via Decoding Dynamics
Query position is a first-order variable in dLLM ICL whose variance matches semantic quality impact; mitigated via Average Confidence metric and training-free Auto-ICL routing.
-
Mixture of Heterogeneous Grouped Experts for Language Modeling
MoHGE achieves standard MoE performance with 20% fewer parameters and balanced GPU utilization via grouped heterogeneous experts, two-level routing, and specialized auxiliary losses.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
Temporally Extended Mixture-of-Experts Models
Temporally extended MoE layers using the option-critic framework with deliberation costs cut switching rates below 5% while retaining most capability on MATH, MMLU, and MMMLU.
-
From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
LLM 2-bit quantization fails via either cumulative signal degradation or early computation collapse in key components.
-
Are Large Language Models Economically Viable for Industry Deployment?
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.
-
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
-
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
ARES discovers dual vulnerabilities in LLMs and reward models via adaptive adversarial prompt composition and repairs them through sequential fine-tuning of the reward model followed by policy optimization.
-
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
BAR trains independent domain experts via separate mid-training, SFT, and RL pipelines then composes them with a MoE router to match monolithic retraining performance at lower cost and without catastrophic forgetting.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum
AIT Academy introduces a tripartite curriculum for AI agents across natural science, humanities, and social science domains, with reported gains of 15.9 points in security and 7 points in social reasoning under specific scheduling.
-
Phase-Scheduled Multi-Agent Systems for Token-Efficient Coordination
PSMAS reduces token use in LLM multi-agent systems by 27.3% on average via phase-based temporal scheduling and context compression, with task performance staying within 2.1 points of full activation.
-
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
A 3B model trained via clarification-aware RLVR improves abstention and post-refusal clarification on unanswerable queries while matching larger models like DeepSeek-R1 on benchmarks.
-
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
SPS interleaves RL and IRL to counteract probability squeezing in LLM reasoning trajectories, improving Pass@k on five benchmarks while identifying an empirical upper bound on multi-sample performance.
-
Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
A training-free method improves epistemic faithfulness of LLM textual explanations by guiding generation with attribution-based attention interventions.
-
Parcae: Scaling Laws For Stable Looped Language Models
Parcae stabilizes looped LLMs via spectral norm constraints on injection parameters, enabling power-law scaling for training FLOPs and saturating exponential scaling at test time that improves quality over fixed-depth baselines under fixed parameter budgets.
-
RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents
RPA-Check is a new multi-stage framework using dimension definition, boolean checklist augmentation, semantic filtering, and LLM-as-judge verification to assess role-playing agents, with tests on a legal training game showing smaller instruction-tuned models can be more consistent than larger ones.
-
Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees
POES frames prompt evaluation as online adaptive testing and uses a provably submodular objective to pick informative examples, delivering 6.2% higher average accuracy and 35-60% token savings versus naive full-set scoring.
-
Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
LIRA aligns latent instruction representations in LLMs to defend against jailbreaks, backdoors, and undesired knowledge, blocking over 99% of PEZ attacks and achieving optimal WMDP forgetting.
-
Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
Loss-based pruning of training data to limit facts and flatten their frequency distribution enables a 110M-parameter GPT-2 model to memorize 1.3 times more entity facts than standard training, matching a 1.3B-parameter model on the full dataset.
-
Sensitivity-Positional Co-Localization in GQA Transformers
In Llama 3.1 8B, task-sensitive layers cluster late while RoPE adaptation is strongest early, yet applying both adaptations only to sensitivity-identified layers outperforms other layer choices by 4-16 points on MMLU, GPQA, HumanEval+, MATH, MGSM and ARC.
-
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge
ChainFed achieves memory-efficient private LLM fine-tuning on edge devices through sequential layer-by-layer adapter training with dynamic co-tuning, perceptive optimization, and adaptive starting point selection, improving accuracy by up to 46.46%.
-
In-Place Test-Time Training
In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.
-
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
JailAgent red-teams LLM agents by hijacking reasoning trajectories and tightening constraints without prompt changes, claiming strong cross-model and cross-scenario performance.
-
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting
CoT2Edit trains LLMs to reason over edited knowledge using agent-generated CoTs, SFT, GRPO, and RAG, achieving generalization across six editing scenarios on three models.