I-X Seminar

Dr Pasquale Minervini (University of Edinburgh) will be delivering the next I-X seminar, entitled “Integrating Symbolic Algorithms in Neural Models (and LLMs)”.

Seminar Summary

Neural models, including LLMs, can exhibit remarkable abilities; paradoxically, they also struggle with algorithmic tasks where much simpler models excel. To solve these issues, we propose Implicit Maximum Likelihood Estimation (IMLE), a framework for end-to-end learning of models combining algorithmic combinatorial solvers and differentiable neural components, which allows us to incorporate planning and reasoning algorithms in neural architectures by just adding a simple decorator. Finally, we’ll discuss some very recent extensions of these ideas for making LLMs teach themselves how to use tools.

Hybrid event: I-X LRT608A level 6 (I-HUB) & via Teams