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.
hub Tool reference
Measuring massive multitask language understanding.Proceedings of the International Conference on Learning Representations (ICLR)
Tool reference. 80% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
14
Pith papers citing it
Method reference
80% of classified citations
hub tools
citation-role summary
dataset 4
background 1
citation-polarity summary
representative citing papers
A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.
DCDM replaces positional blocks with learnable semantic chunks via differentiable Chunking Attention, yielding consistent gains over block and unstructured diffusion baselines up to 1.5B parameters.
Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
LogiHard hardens reasoning benchmarks by transforming 0-order selection into 2-order judgment, causing 31-56% accuracy drops in 12 frontier LLMs and a 47% drop on zero-shot MMLU, revealing a combinatorial reasoning gap rather than knowledge deficits.
EMO pretrains MoEs using document boundaries to induce semantic expert specialization, enabling modular subset deployment with minimal accuracy loss unlike standard MoEs.
An ensemble-based information-theoretic active learning method using ensemble Kalman inversion selects valuable tasks to optimize communication structures in LLM multi-agent systems more reliably than random sampling under limited training budgets.
PIA achieves lower attack success rates on persona-based jailbreaks via self-play co-evolution of attacks (PLE) and defenses (PICL) that structurally decouples safety from persona context using unilateral KL-divergence.
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
RLVR exhibits implicit reward overfitting to training data and optimizes heavy-tailed singular spectra with rank-1 focus on reasoning capability.
SPON adds a small set of trainable input-independent activation vectors as representational anchors, trained by distribution matching, to stabilize sparse activation in LLMs and recover performance lost to hidden-state distribution shifts.
Taklif.AI generates interest-based personalized college assignments via LLMs with prompt engineering and guardrails, receiving positive feedback from 84% of 68 preliminary users.
A multi-dimensional audit framework for politically aligned LLMs finds consistent trade-offs: larger models are more effective and truthful but less fair with higher bias, while fine-tuned models reduce bias but increase hallucinations and reasoning decline, and all tested models show deficiencies.
citing papers explorer
-
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.
-
Self-Improving In-Context Learning
A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.
-
Dynamic Chunking for Diffusion Language Models
DCDM replaces positional blocks with learnable semantic chunks via differentiable Chunking Attention, yielding consistent gains over block and unstructured diffusion baselines up to 1.5B parameters.
-
Rethinking Vacuity for OOD Detection in Evidential Deep Learning
Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.
-
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
-
From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs
LogiHard hardens reasoning benchmarks by transforming 0-order selection into 2-order judgment, causing 31-56% accuracy drops in 12 frontier LLMs and a 47% drop on zero-shot MMLU, revealing a combinatorial reasoning gap rather than knowledge deficits.
-
EMO: Pretraining Mixture of Experts for Emergent Modularity
EMO pretrains MoEs using document boundaries to induce semantic expert specialization, enabling modular subset deployment with minimal accuracy loss unlike standard MoEs.
-
Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
An ensemble-based information-theoretic active learning method using ensemble Kalman inversion selects valuable tasks to optimize communication structures in LLM multi-agent systems more reliably than random sampling under limited training budgets.
-
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
PIA achieves lower attack success rates on persona-based jailbreaks via self-play co-evolution of attacks (PLE) and defenses (PICL) that structurally decouples safety from persona context using unilateral KL-divergence.
-
Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
-
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
RLVR exhibits implicit reward overfitting to training data and optimizes heavy-tailed singular spectra with rank-1 focus on reasoning capability.
-
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
SPON adds a small set of trainable input-independent activation vectors as representational anchors, trained by distribution matching, to stabilize sparse activation in LLMs and recover performance lost to hidden-state distribution shifts.
-
Taklif.AI: LLM-Powered Platform for Interest-Based Personalized College Assignments
Taklif.AI generates interest-based personalized college assignments via LLMs with prompt engineering and guardrails, receiving positive feedback from 84% of 68 preliminary users.
-
A Multi-Dimensional Audit of Politically Aligned Large Language Models
A multi-dimensional audit framework for politically aligned LLMs finds consistent trade-offs: larger models are more effective and truthful but less fair with higher bias, while fine-tuned models reduce bias but increase hallucinations and reasoning decline, and all tested models show deficiencies.