Moussa Koulako Bala Doumbouya — accepted AI-conference papers

2026

CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition

Martijn Bartelds, Ananjan Nandi, Moussa Koulako Bala Doumbouya, Dan Jurafsky, Tatsunori Hashimoto, Karen Livescu

ICLR 2026poster

Modern deep learning models often achieve high overall performance, but consistently fail on specific subgroups. Group distributionally robust optimization (group DRO) addresses this problem by minimizing the worst-group loss, but it fails when group losses misrepresent performance differences betwe…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity

Moussa Koulako Bala Doumbouya, Dan Jurafsky, Christopher D Manning

ICLR 2026poster

Work in psychology has highlighted that the geometric model of similarity standard in deep learning is not psychologically plausible because its metric properties such as symmetry do not align with human perception of similarity. In contrast, (Tversky,1977) proposed an axiomatic theory of simila…

Cited by 0 Source ↗code ↗Scholar ↗

2025

h4rm3l: A Language for Composable Jailbreak Attack Synthesis

Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi +2

ICLR 2025poster

Despite their demonstrated valuable capabilities, state-of-the-art (SOTA) widely deployed large language models (LLMs) still have the potential to cause harm to society due to the ineffectiveness of their safety filters, which can be bypassed by prompt transformations called jailbreak attacks. Curre…

Cited by 0 Source ↗PDF ↗Scholar ↗