Portrait de Istabrak Abbes n'est pas disponible

Istabrak Abbes

Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e
Sarath Chandar
Sujets de recherche
Apprentissage continu
Apprentissage profond
Traitement du langage naturel

Publications

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
Istabrak Abbes
Gopeshh Subbaraj
Matthew D Riemer
Nizar Islah
Benjamin Therien
Tsuguchika Tabaru
Hiroaki Kingetsu
A. Chandar
Irina Rish
2025-09-21
NeurIPS.cc/2025/Workshop/WiML (publié)
doi.org
openreview.net
Small Encoders Can Rival Large Decoders in Detecting Groundedness
Istabrak Abbes
Gabriele Prato
Quentin Fournier
Fernando Rodriguez
Alaa Boukhary
Adam Elwood
A. Chandar
Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) … (voir plus)tasks. However, LLMs struggle to answer queries reliably when the provided context lacks information, often resorting to ungrounded speculation or internal knowledge. Groundedness - generating responses strictly supported by the context - is essential for ensuring factual consistency and trustworthiness. This study focuses on detecting whether a given query is grounded in a document provided in context before the costly answer generation by LLMs. Such a detection mechanism can significantly reduce both inference time and resource consumption. We show that lightweight, task specific encoder models such as RoBERTa and NomicBERT, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs, such as Llama3 8B and GPT4o, in groundedness detection while reducing inference latency by orders of magnitude. The code is available at : https://github.com/chandarlab/Hallucinate-less
2025-06-25
ArXiv (prépublication)
doi.org
arxiv.org