Inverse Language Modeling towards Robust and Grounded LLMs
This addresses the need for more robust and controllable LLMs, potentially aiding in RED teaming and enhancing trustworthiness, though it appears incremental as it builds on existing concepts of adversarial robustness.
The paper tackles the problem of fragmented defensive mechanisms for LLMs by proposing Inverse Language Modeling (ILM), a unified framework that improves robustness to input perturbations and enables native grounding to identify unsafe input triggers, transforming LLMs into analyzable and robust systems.
The current landscape of defensive mechanisms for LLMs is fragmented and underdeveloped, unlike prior work on classifiers. To further promote adversarial robustness in LLMs, we propose Inverse Language Modeling (ILM), a unified framework that simultaneously 1) improves the robustness of LLMs to input perturbations, and, at the same time, 2) enables native grounding by inverting model outputs to identify potentially toxic or unsafe input triggers. ILM transforms LLMs from static generators into analyzable and robust systems, potentially helping RED teaming. ILM can lay the foundation for next-generation LLMs that are not only robust and grounded but also fundamentally more controllable and trustworthy. The code is publicly available at github.com/davegabe/pag-llm.