LLM residual streams during addition form an Iso-Raw-Sum Trajectory anchored by digit semantics and modulated by continuous carry signals, with errors arising as geometric slippages across quantization thresholds in a noisy model.
arXiv preprint arXiv:2510.05969 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Preregistered behavioral study identifies a speedup illusion where users overestimate time savings from AI assistance on cognitive tasks despite no actual difference in completion times.
After length correction, reasoning-trained language models exhibit distinct hidden-state trajectory geometries on harder problems compared to instruction-tuned baselines, with the strongest effect in code domains.
DARE co-evolves difficulty estimation and policy in RL for LLMs to improve training efficiency, final performance, and inference speed by using tailored strategies for different difficulty levels.
RouteLMT learns to route MT requests to large or small LLMs by predicting marginal quality gain from small-model token representations, yielding a better quality-budget Pareto frontier than baselines.
citing papers explorer
-
The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models
LLM residual streams during addition form an Iso-Raw-Sum Trajectory anchored by digit semantics and modulated by continuous carry signals, with errors arising as geometric slippages across quantization thresholds in a noisy model.
-
Cognitive offloading and the speedup illusion in human-AI interaction
Preregistered behavioral study identifies a speedup illusion where users overestimate time savings from AI assistance on cognitive tasks despite no actual difference in completion times.
-
Reasoning Models Don't Just Think Longer, They Move Differently
After length correction, reasoning-trained language models exhibit distinct hidden-state trajectory geometries on harder problems compared to instruction-tuned baselines, with the strongest effect in code domains.
-
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
DARE co-evolves difficulty estimation and policy in RL for LLMs to improve training efficiency, final performance, and inference speed by using tailored strategies for different difficulty levels.
-
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
RouteLMT learns to route MT requests to large or small LLMs by predicting marginal quality gain from small-model token representations, yielding a better quality-budget Pareto frontier than baselines.