TraceGuard formulates antidistillation as a detectability-constrained Stackelberg game and poisons sparsely located thought anchors via branching-token detection to degrade student models while preserving trace quality.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
DialectLLM generates parallel multi-dialect dialog data and a 50k-dialog benchmark showing frontier LLMs achieve under 70% accuracy on dialect tasks while the generated data can improve post-training.
Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.
RE-TAB uses a deterministic LCS-based table-state reward for stepwise guidance and test-time scaling, raising LLM table-reasoning accuracy by 26.7 pp on average across six backbones and three benchmarks.
citing papers explorer
-
Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
TraceGuard formulates antidistillation as a detectability-constrained Stackelberg game and poisons sparsely located thought anchors via branching-token detection to degrade student models while preserving trace quality.
-
DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
DialectLLM generates parallel multi-dialect dialog data and a 50k-dialog benchmark showing frontier LLMs achieve under 70% accuracy on dialect tasks while the generated data can improve post-training.
-
Privacy Attacks on Image AutoRegressive Models
Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.
-
Enhancing Table Reasoning with Deterministic Table-State Rewards
RE-TAB uses a deterministic LCS-based table-state reward for stepwise guidance and test-time scaling, raising LLM table-reasoning accuracy by 26.7 pp on average across six backbones and three benchmarks.