Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
A recent study titled 'Teaching Transformers Causal Reasoning through Axiomatic Training' by Aniket Vashishtha, Abhinav Kumar, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian, and Amit Sharma, published on July 11, 2024, proposes a new paradigm for training language models. The study introduces an Axiomatic Framework, where a 67-million-parameter model trained from scratch on simple causal chains outperforms billion-scale language models and rivals GPT-4 in inferring cause-effect relations over complex graphs. This research aims to explore whether transformers can be taught causal reasoning effectively through axiomatic training.
Teaching Transformers Causal Reasoning through Axiomatic Training Vashishtha et al.: https://t.co/L5rWkgZ2Im #ArtificialIntelligence #CausalReasoning #DeepLearning https://t.co/PRmDimkSEL
CoGS: Causality Constrained Counterfactual Explanations using goal-directed ASP https://t.co/RhM2QYs7CB
Can we teach Transformers Causal Reasoning? We propose Axiomatic Framework, a new paradigm for training LMs. Our 67M-param model, trained from scratch on simple causal chains, outperforms billion-scale LLMs and rivals GPT-4 in inferring cause-effect relations over complex graphs https://t.co/caltWON6CG
