← Search

Vincent Guigue

4 accepted papers

2025

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

ICLR 2025poster

Large Language Models (LLMs), when used for conditional text generation, often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This issue arises in typical conditional text generation tasks, such as text summarization and data-to-text generation, wh…

Cited by 0SourcePDFScholar
2023

Improving generalization in large langue model by learning prefix subspaces

EMNLP 2023long findings

This article focuses on large language models (LLMs) fine-tuning in the scarce data regime (also known as "few-shot learning setting"). We propose a method to increase the generalization capabilities of LLMs based on neural network subspaces. This optimization method, recently introduced in comput…

Cited by 0SourceScholar
2021

Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction

EMNLP 2021main

State-of-the-art NLP models can adopt shallow heuristics that limit their generalization capability (McCoy et al., 2019). Such heuristics include lexical overlap with the training set in Named-Entity Recognition (Taille et al., 2020) and Event or Type heuristics in Relation Extraction (Rosenman et a…

2021

Towards Rigorous Interpretations: a Formalisation of Feature Attribution

ICML 2021spotlight

Feature attribution is often loosely presented as the process of selecting a subset of relevant features as a rationale of a prediction. Task-dependent by nature, precise definitions of "relevance" encountered in the literature are however not always consistent. This lack of clarity stems from the f…