DOLORES, an agent using a formal language for meta-reasoning to construct adaptive scaffolds on the fly, outperforms prior scaffolding methods by 24.8% on average across four hard benchmarks and multiple model sizes.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
A user study finds that LLM reasoning traces and post-hoc explanations create false trust by increasing acceptance of incorrect answers, whereas contrastive dual explanations improve users' ability to detect errors.
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
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.
ReSS uses decision-tree scaffolds to fine-tune LLMs for faithful tabular reasoning, reporting up to 10% gains over baselines on medical and financial data.
RLVR incentivizes correct reasoning in base LLMs, extending reasoning boundaries on math and coding tasks as shown by CoT-Pass@K evaluations and a theoretical incentive framework.
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
citing papers explorer
-
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.
-
Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
-
ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold
ReSS uses decision-tree scaffolds to fine-tune LLMs for faithful tabular reasoning, reporting up to 10% gains over baselines on medical and financial data.
-
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
RLVR incentivizes correct reasoning in base LLMs, extending reasoning boundaries on math and coding tasks as shown by CoT-Pass@K evaluations and a theoretical incentive framework.
-
LLM Reasoning Is Latent, Not the Chain of Thought
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.