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%).
520
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 31
dataset 30
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).
Sumi is an openly released 7B parameter uniform diffusion language model pretrained from scratch on 1.5T tokens that matches autoregressive models on several benchmarks.
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.
ELDR reduces median TPOT by 5.9-13.9% in PD-disaggregated MoE serving via expert signatures from prefill, K-means partitioning, and locality-band routing with KV-co-indexed signature cache.
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.
ICT framework applies JS divergence to token logits to select critical tokens for selective RLVR updates, claiming 4.58% average pass@4 gains on Qwen2.5 models across seven reasoning benchmarks.
SIGMA introduces skill-incidence graphs to compose agents from reusable skills, yielding higher average performance and robustness than topology-only baselines on reasoning and coding benchmarks.
For balanced Gaussian class projections, OOD AUROC is a linear function of MCS to the reference probe because both are sigmoid-shaped functions of the probe SNR on test data.
MergeProbe forecasts LoRA adapter mergeability from first-few-percent training signals and outperforms interference-aware baselines on retention while adding low overhead on a five-domain benchmark.
Block-size curriculum learning trains an 8B diffusion model to achieve competitive reasoning performance on math and code benchmarks by transitioning from small to large training block sizes.
Presents a distribution-aware scheduling framework for LLM inference that reduces P99 TTLT by 35-50% and TTFT by 34-47% versus SRPT with perfect length knowledge using statistical signals instead of predictions.
ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.
citing papers explorer
-
Bad company corrupts good morals: Understanding and Measuring Narrative-Induced Moral Reasoning Degradation in LLMs
Negative narrative immersion causes 12-31% drops in LLM moral accuracy and produces structured shifts that appear in downstream applications.
-
DataComp-VLM: Improved Open Datasets for Vision-Language Models
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).
-
Sumi: Open Uniform Diffusion Language Model from Scratch
Sumi is an openly released 7B parameter uniform diffusion language model pretrained from scratch on 1.5T tokens that matches autoregressive models on several benchmarks.
-
Fully Open Meditron: An Auditable Pipeline for Clinical LLMs
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.
-
Unsteady Metrics and Benchmarking Cultures of AI Model Builders
AI model builders mostly highlight unique benchmarks that act as flexible narrative tools for market positioning rather than standardized scientific measurements.
-
HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts
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: Benchmarking LLM Agents on Live Energy Infrastructure Data
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.
-
Crafting Reversible SFT Behaviors in Large Language Models
LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
-
ArgBench: Benchmarking LLMs on Computational Argumentation Tasks
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: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
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.
-
Large Language Diffusion Models
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: 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.
-
Will Scaling Improve Social Simulation with LLMs?
Scaling improves LLM social simulation fidelity in most opinion and behavior tasks but not for human cognitive bias calibration or low-resource domains.
-
Meta-Benchmarks for Financial-Services LLM Evaluation
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.
-
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
ELDR reduces median TPOT by 5.9-13.9% in PD-disaggregated MoE serving via expert signatures from prefill, K-means partitioning, and locality-band routing with KV-co-indexed signature cache.
-
FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks
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.
-
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
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.
-
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
ICT framework applies JS divergence to token logits to select critical tokens for selective RLVR updates, claiming 4.58% average pass@4 gains on Qwen2.5 models across seven reasoning benchmarks.
-
SIGMA: Skill-Incidence Graphs for Compositional Multi-Agent Design
SIGMA introduces skill-incidence graphs to compose agents from reusable skills, yielding higher average performance and robustness than topology-only baselines on reasoning and coding benchmarks.
-
Comparing Linear Probes with Mahalanobis Cosine Similarity
For balanced Gaussian class projections, OOD AUROC is a linear function of MCS to the reference probe because both are sigmoid-shaped functions of the probe SNR on test data.
-
Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates
MergeProbe forecasts LoRA adapter mergeability from first-few-percent training signals and outperforms interference-aware baselines on retention while adding low overhead on a five-domain benchmark.
-
DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models
Block-size curriculum learning trains an 8B diffusion model to achieve competitive reasoning performance on math and code benchmarks by transitioning from small to large training block sizes.
-
Beyond Prediction: Tail-Aware Scheduling for LLM Inference
Presents a distribution-aware scheduling framework for LLM inference that reduces P99 TTLT by 35-50% and TTFT by 34-47% versus SRPT with perfect length knowledge using statistical signals instead of predictions.
-
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.
-
Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation
CEO-Bench evaluates LLMs on CEO-level strategic resource reallocation via multi-role agent simulations, showing high structural validity but sharp divergence on strategic calibration across five frontier models on 13 scenarios.
-
Unified Energy for Invariant and Independent Decoding in Diffusion Language Models
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: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models
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: Efficient Data Selection for Finetuning Large Language Models
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 Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
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*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios
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.
-
Knowledge Index of Noah's Ark
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%.
-
Toward Calibrated, Fair, and accurate Deepfake Detection
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: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
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: A Workflow-Grounded Benchmark for Financial-Research Agents
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.
-
Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference
A new fault-injection framework enables a systematic empirical study that produces 17 takeaways on error propagation in LLM inference and four software-only mitigation directions.
-
CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs
CultureForest benchmark shows top LLMs degrade sharply on open-ended cultural reasoning tasks, exhibit regional disparities, and are limited more by effective use of knowledge than by lack of knowledge itself.
-
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
THRD introduces a training-free multi-turn defense framework that models temporal risk accumulation to reduce jailbreak attack success rates to 0.2-4.0% on LLMs with under 1.5% utility degradation.
-
From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
A bipartite factor graph with message-passing protocol and asymmetric damping aggregates multi-LLM predictions, cutting token use by 97% and API calls by 6X while outperforming baselines on MMLU, MMLU-Pro, GPQA, and MedMCQA.
-
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
RHELM is a benchmark for LLM long-term memory with dynamic profiles, heterogeneous sources, and 27 memory characteristics that reveals weaknesses in existing models for multi-source aggregation and contextual reasoning.
-
ReactBench: A Cause-Driven Benchmark for Multimodal Hallucination via Systematic Evaluation
ReactBench is a new benchmark with four cause-targeted tasks that uses adversarial images, hallucination-inducing queries, and Chain-of-Thought analysis to expose specific failure modes in current multimodal large language models.
-
K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance
K-FinHallu is the first multi-turn Korean financial RAG hallucination benchmark; frontier LLMs struggle especially on justified abstention while an 8B fine-tuned model reaches competitive performance.
-
ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression
ConMoE consolidates MoE experts into a smaller prototype pool via deterministic remapping based on contribution and replaceability, matching or beating pruning/merging baselines at 25-50% reduction on three models.
-
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?
LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
-
SiDP: Memory-Efficient Data Parallelism for Offline LLM Inference
SiDP distributes model weights across a DP group with WaS and CaS modes to increase KV cache capacity by up to 1.8x and end-to-end throughput by up to 1.5x over vLLM on H20/H200/B200 GPUs for offline LLM inference.
-
A Policy-Driven Runtime Layer for Agentic LLM Serving
Introduces a three-tier architecture with an agent runtime layer and four primitives for agent-aware policies in LLM serving, validated on KV caching via CacheSage showing 13-37pp hit-rate gains on five workloads.
-
JobBench: Aligning Agent Work With Human Will
JobBench is a new benchmark with 130 occupational tasks where the best of 36 tested AI models achieves only 45.9% success.
-
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
ARBITER models reasoning trajectory basins in test-time sampling and uses model-internal signals to correct majority-vote failures, recovering part of the oracle gap on math benchmarks.
-
Self-Policy Distillation via Capability-Selective Subspace Projection
Self-Policy Distillation extracts a capability subspace from model gradients on correctness tokens, projects KV activations into it for self-generation, and fine-tunes LLMs to achieve up to 13-16% gains over baselines without external signals.
-
X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
X-Token proposes projection-guided P-KL and H-KL losses to fix uncommon-token suppression and over-conservative matching in logit-based cross-tokenizer distillation, yielding gains over GOLD on Llama-3.2-1B.
-
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
The paper introduces an outlier-injection attack that induces targeted weight collapse in LLMs under advanced quantization schemes including AWQ, GPTQ, and GGUF I-quants.