Cover Image

LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mondorf, Philipp, Bell, Samuel J., Dodge, Jesse, Hupkes, Dieuwke
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Compute Optimal Scaling of Skills: Knowledge vs Reasoning
by: Roberts, Nicholas, et al.
Published: (2025)

Quantifying Variance in Evaluation Benchmarks
by: Madaan, Lovish, et al.
Published: (2024)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
by: Mondorf, Philipp, et al.
Published: (2024)

MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages
by: Hupkes, Dieuwke, et al.
Published: (2025)

Brittlebench: Quantifying LLM robustness via prompt sensitivity
by: Romanou, Angelika, et al.
Published: (2026)

ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale
by: Thomas, Noel
Published: (2026)

From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency
by: Ohmer, Xenia, et al.
Published: (2024)

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
by: Eichin, Florian, et al.
Published: (2025)

Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks
by: Schaeffer, Rylan, et al.
Published: (2025)

Reason to Rote: Rethinking Memorization in Reasoning
by: Du, Yupei, et al.
Published: (2025)

Holistically Evaluating the Environmental Impact of Creating Language Models
by: Morrison, Jacob, et al.
Published: (2025)

LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
by: Long, Yunbo, et al.
Published: (2025)

Difficulties with Evaluating a Deception Detector for AIs
by: Smith, Lewis, et al.
Published: (2025)

On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark
by: Fairoze, Jaiden, et al.
Published: (2025)

Fake News Detection After LLM Laundering: Measurement and Explanation
by: Das, Rupak Kumar, et al.
Published: (2025)

Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment
by: Li, Cheryl, et al.
Published: (2025)

Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation
by: Heineman, David, et al.
Published: (2025)

Evaluating Game Difficulty in Tetris Block Puzzle
by: Wang, Chun-Jui, et al.
Published: (2026)

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
by: Mondorf, Philipp, et al.
Published: (2024)

LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance
by: Haller, Patrick, et al.
Published: (2025)

Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training
by: Wu, Zihui, et al.
Published: (2022)

The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
by: Bell, Samuel J., et al.
Published: (2024)

Evaluating the Robustness of Chinchilla Compute-Optimal Scaling
by: Schaeffer, Rylan, et al.
Published: (2025)

Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
by: Liu, Siyuan, et al.
Published: (2026)

Reassessing the Validity of Spurious Correlations Benchmarks
by: Bell, Samuel J., et al.
Published: (2024)

Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs
by: Yadav, Suraj, et al.
Published: (2026)

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
by: Luo, Qin-Wen, et al.
Published: (2026)

Interpretability of Language Models via Task Spaces
by: Weber, Lucas, et al.
Published: (2024)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
by: Sun, Yifan, et al.
Published: (2025)

Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens
by: Nikolaou, Konstantin, et al.
Published: (2025)

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
by: Chen, Tianhao, et al.
Published: (2025)

Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
by: Jandali, Yaman, et al.
Published: (2025)

Circuit Transformer: A Transformer That Preserves Logical Equivalence
by: Li, Xihan, et al.
Published: (2024)

Scaling Up Diffusion and Flow-based XGBoost Models
by: Cresswell, Jesse C., et al.
Published: (2024)

Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores
by: Robertson, Zachary
Published: (2025)

Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
by: Kurian, Nikhil Cherian, et al.
Published: (2026)

D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
by: Zhang, Jia, et al.
Published: (2025)

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
by: Schneider, Chris, et al.
Published: (2026)

Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation
by: Kricheli, Joshua Shay, et al.
Published: (2026)

LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detection
by: Zhang, Haoting, et al.
Published: (2026)