6 papers
Abductive Reasoning with Probabilistic Commonsense
Joseph Cotnareanu, Chiara Roverato, Han Zhou +3
Recent efforts to improve the reasoning abilities of Large Language Models (LLMs) have focused on integrating formal logic solvers within neurosymbolic frameworks. A key challenge…
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Chris Cameron, Wangzheng Wang, Nikita Ivanov +3
Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where e…
A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
Joseph Cotnareanu, Didier Chetelat, Yingxue Zhang +1
Although Large Language Models (LLMs) have demonstrated impressive formal reasoning abilities, they often break down when problems require complex proof planning. One promising app…
Refining Answer Distributions for Improved Large Language Model Reasoning
Soumyasundar Pal, Didier Chételat, Yingxue Zhang +1
Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Rea…
The Graph's Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimation
Reza Moravej, Saurabh Bodhe, Zhanguang Zhang +6
Logic synthesis is a crucial phase in the circuit design process, responsible for transforming hardware description language (HDL) designs into optimized netlists. However, traditi…
InnerThoughts: Disentangling Representations and Predictions in Large Language Models
Didier Chételat, Joseph Cotnareanu, Rylee Thompson +2
Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the pro…