2 citations · 3 across the 7 of their papers we have counts for
6 papers · 1 filter
LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders
Wissam Antoun, Francis Kulumba, Théo Lasnier +2
Even though backdoors in LLMs have been a growing concern, their inner workings are still under heavy scrutiny. Trigger-based backdoors are easy to define behaviorally, a rare inpu…
Language-Switching Triggers Take a Latent Detour Through Language Models
Francis Kulumba, Wissam Antoun, Théo Lasnier +2
Backdoor attacks on language models pose a growing security concern, yet the internal mechanisms by which a trigger sequence hijacks model computations remain poorly understood. We…
BigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?
Pierre Chambon, Baptiste Roziere, Benoit Sagot +1
We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and…
Spirit LM: Interleaved Spoken and Written Language Model
Tu Anh Nguyen, Benjamin Muller, Bokai Yu +13
We introduce Spirit LM, a foundation multimodal language model that freely mixes text and speech. Our model is based on a 7B pretrained text language model that we extend to the sp…
XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words
Robin Algayres, Pablo Diego-Simon, Benoit Sagot +1
Due to the absence of explicit word boundaries in the speech stream, the task of segmenting spoken sentences into word units without text supervision is particularly challenging. I…
Generative Spoken Language Model based on continuous word-sized audio tokens
Robin Algayres, Yossi Adi, Tu Anh Nguyen +4
In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs a…