Behavior Forecasters trained on LRM trajectories outperform larger models in predicting repeatability and input sensitivity at low cost.
hub
On the hardness of faithful chain-of-thought reasoning in large language models
14 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
14
Pith papers citing it
1
external citations · external index
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
Empirical study finds isolation drives gains for weak models in multi-agent RAG while scoring matters for strong ones, enabling MADARA for cost-efficient adaptive assessment.
HANSEL extracts navigable evidence from agent trajectories with 83.7% precision and 88.8% recall on 45 tasks, reduces volume by 61.6%, and improves verification metrics in a 14-participant study.
CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
LLMs have linearly decodable functional metacognitive states that causally modulate reasoning when steered via activation interventions.
Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
Closed-system multi-step LLM reasoning is subject to an information-theoretic bound where mutual information with evidence decreases, preserving accuracy while eroding faithfulness, with EGSR recovering it on SciFact and FEVER.
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
Chain-of-thought steps in LLMs vary in causal influence; many are decorative, TTS identifies them, and a latent steering direction can switch whether a model 'thinks' through a step.
Reasoning in LLMs emerges from inference dynamics forming constrained low-dimensional manifolds that preserve non-degenerate information volume, rather than from compression alone.
OpenAI reports that chain-of-thought reasoning in o1 models enables deliberative alignment, yielding state-of-the-art results on selected safety benchmarks for illicit advice, stereotypes, and jailbreaks.
citing papers explorer
-
Forecasting Future Behavior as a Learning Task
Behavior Forecasters trained on LRM trajectories outperform larger models in predicting repeatability and input sensitivity at low cost.
-
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
-
To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG
Empirical study finds isolation drives gains for weak models in multi-agent RAG while scoring matters for strong ones, enabling MADARA for cost-efficient adaptive assessment.
-
HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification
HANSEL extracts navigable evidence from agent trajectories with 83.7% precision and 88.8% recall on 45 tasks, reduces volume by 61.6%, and improves verification metrics in a 14-participant study.
-
When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
-
Decomposing and Steering Functional Metacognition in Large Language Models
LLMs have linearly decodable functional metacognitive states that causally modulate reasoning when steered via activation interventions.
-
Understanding Annotator Safety Policy with Interpretability
Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
-
The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
Closed-system multi-step LLM reasoning is subject to an information-theoretic bound where mutual information with evidence decreases, preserving accuracy while eroding faithfulness, with EGSR recovering it on SciFact and FEVER.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
Chain-of-thought steps in LLMs vary in causal influence; many are decorative, TTS identifies them, and a latent steering direction can switch whether a model 'thinks' through a step.
-
Reasoning emerges from constrained inference manifolds in large language models
Reasoning in LLMs emerges from inference dynamics forming constrained low-dimensional manifolds that preserve non-degenerate information volume, rather than from compression alone.
-
OpenAI o1 System Card
OpenAI reports that chain-of-thought reasoning in o1 models enables deliberative alignment, yielding state-of-the-art results on selected safety benchmarks for illicit advice, stereotypes, and jailbreaks.
- Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers
- Understanding and Mitigating Premature Confidence for Better LLM Reasoning