We have 4 of 21 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstream prediction. However, prior work demonstrated that LLMs struggle to use representations learned in context on a graph tracking task, where...
The neurofeedback paradigm for LLMs is redesigned so that the control target satisfies the privileged access requirement, which is closer to neurofeedback experiments in human cognitive neuroscience and indicates that rigorous assessments of metacognition in LLMs require evaluation methods that demand privileged access...
A symbolic-attribute oracle shows that CoT can improve counting once ground-truth attributes are supplied as text, while a single-object probe-vs-decode check shows that hard attributes can be linearly recoverable from hidden states yet difficult for the model itself to output.
A taxonomy of CoT is proposed consisting of Explicit CoT, which outputs all operations without aggregation, Composed CoT, which combines multiple operations into a single step, and Implicit CoT, which omits intermediate operations.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
