ProofWriter
PulseAugur coverage of ProofWriter — every cluster mentioning ProofWriter across labs, papers, and developer communities, ranked by signal.
-
New AtManRL method enhances LLM reasoning faithfulness
Researchers have developed a new method called AtManRL to improve the faithfulness of chain-of-thought reasoning in large language models. This technique uses differentiable attention manipulation and reinforcement lear…
-
Typed decision models offer cost-effective alternative to LLMs for tabular data
Researchers have developed "typed decision models" that are designed to answer questions with a fixed set of possible answers, rather than generating free-form text. These models, when applied to tabular data, perform c…
-
New research explores recurrent and latent implicit reasoning in LLMs
Two new research papers explore methods to improve implicit reasoning in large language models (LLMs). The first paper introduces "Recurrent-Depth Transformers" which use iterative computation over the same transformer …