Lightweight Latent Reasoning for Narrative Tasks
Trains a small projector to replace parts of a written reasoning trace with continuous embeddings. Reinforcement learning teaches the language model when to use these latent steps for plot-hole detection and story generation.
First public: · Added to this list: November 3, 2026
Cite this paper
Published version
Lightweight Latent Reasoning for Narrative Tasks
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata
Transactions of the Association for Computational Linguistics, 2026, pp. 2163-2186.
Explore this approach
Internalized reasoning — Learn from worked solutions so that some or all of the reasoning can later happen without writing those steps. Training may use a separate teacher model or progressively remove written steps from the model being trained.
Continuous-state reasoning — Use vectors—lists of numbers—to carry intermediate reasoning from one step to the next, instead of selecting a text token at every step. Some methods use the model's hidden states; others combine several candidate token representations.