6 papers
Interestingness as an Inductive Heuristic for Future Compression Progress
Vincent Herrmann, Jürgen Schmidhuber
One of the bottlenecks on the way towards recursively self-improving systems is the challenge of interestingness: the ability to prospectively identify which tasks or data hold the…
RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
Dylan R. Ashley, Gaël Le Lan, Changsheng Zhao +7
Large language models (LLMs) face a fundamental trade-off between computational efficiency (e.g., number of parameters) and output quality, especially when deployed on computationa…
Planning to Explore: Curiosity-Driven Planning for LLM Test Generation
Alfonso Amayuelas, Firas Laakom, Piotr Piękos +5
The use of LLMs for code generation has naturally extended to code testing and evaluation. As codebases grow in size and complexity, so does the need for automated test generation.…
Multiple Token Divergence: Measuring and Steering In-Context Computation Density
Vincent Herrmann, Eric Alcaide, Michael Wand +1
Measuring the in-context computational effort of language models is a key challenge, as metrics like next-token loss fail to capture reasoning complexity. Prior methods based on la…
Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks
Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber
There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions. Our artificial scientists not only learn to answer given q…
On Narrative Information and the Distillation of Stories
Dylan R. Ashley, Vincent Herrmann, Zachary Friggstad +1
The act of telling stories is a fundamental part of what it means to be human. This work introduces the concept of narrative information, which we define to be the overlap in infor…