Mid-reasoning shifts in reasoning models are rare symptoms of unstable inference that seldom improve accuracy and do not reflect intrinsic self-correction.
Emergent abilities in large language models: A survey
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A framework encodes observed trajectories and HD maps into tokens for frozen LLMs to perform spatio-temporal reasoning and predict future vehicle paths with a linear decoder.
Proposes a fault-tolerance architecture for AI safety by analogizing unreliable AI artifacts to Byzantine nodes and applying consensus mechanisms.
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
citing papers explorer
-
The Illusion of Insight in Reasoning Models
Mid-reasoning shifts in reasoning models are rare symptoms of unstable inference that seldom improve accuracy and do not reflect intrinsic self-correction.
-
Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction
A framework encodes observed trajectories and HD maps into tokens for frozen LLMs to perform spatio-temporal reasoning and predict future vehicle paths with a linear decoder.
-
A Byzantine Fault Tolerance Approach towards AI Safety
Proposes a fault-tolerance architecture for AI safety by analogizing unreliable AI artifacts to Byzantine nodes and applying consensus mechanisms.
-
Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
- Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
- MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs