5 papers · 1 filter
PatchBench: Measuring Collateral Damage in Activation Patching
Alexi Canesse, Mathis Le Bail, Maël Jenny +3
An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak repairs, where the goal is to correct a specific unsafe behavi…
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Mohamed Dhouib, Clement Elliker, Alexi Canesse +6
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack…
Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification
Jérémie Dentan, Alexi Canesse, Mahammed El Sharkawy +1
Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of each claim in their outputs. We…
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
Alexi Canesse, Benoît Goupil, Jesse Read +1
Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe b…
Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs
Zakaria Baba, Alexandre M. Bayen, Alexi Canesse +7
We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a traina…