2 citations · 2 across the 12 of their papers we have counts for
10 papers · 1 filter
Learning New Facts with QLoRA: An Acquisition-Retention Frontier
Estelle Zheng, Sébastien Warichet, Emmanuel Helbert +1
Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters. We show that this assumption depends stro…
Large Language Models for Citation Function Classification
Daniel Vodička, Jakub Šmíd, Pavel Král +1
Citation function classification plays a crucial role in understanding the relationships between scientific publications and advancing bibliometric analysis. This study presents on…
GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
Gaspard Michel, Elena V. Epure, Romain Hennequin +2
Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another crucial aspect: the textual con…
S-VoCAL: A Dataset and Evaluation Framework for Inferring Speaking Voice Character Attributes in Literature
Abigail Berthe-Pardo, Gaspard Michel, Elena V. Epure +1
With recent advances in Text-to-Speech (TTS) systems, synthetic audiobook narration has seen increased interest, reaching unprecedented levels of naturalness. However, larger gaps…
Cross-lingual Matryoshka Representation Learning across Speech and Text
Yaya Sy, Dioula Doucouré, Christophe Cerisara +1
Speakers of under-represented languages face both a language barrier, as most online knowledge is in a few dominant languages, and a modality barrier, since information is largely…
Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets
Estelle Zheng, Nathan Cerisara, Sébastien Warichet +2
Fine-tuning large language models (LLMs) is often limited by the memory available on commodity GPUs. Parameter-efficient fine-tuning (PEFT) methods such as QLoRA reduce the number…
Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning
Maxime Méloux, Christophe Cerisara
Teaching new information to pre-trained large language models (PLM) is a crucial but challenging task. Model adaptation techniques, such as fine-tuning and parameter-efficient trai…
Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3
Gaspard Michel, Elena V. Epure, Romain Hennequin +1
Large Language Models (LLMs) have shown promising results in a variety of literary tasks, often using complex memorized details of narration and fictional characters. In this work,…
Improving Quotation Attribution with Fictional Character Embeddings
Gaspard Michel, Elena V. Epure, Romain Hennequin +1
Humans naturally attribute utterances of direct speech to their speaker in literary works. When attributing quotes, we process contextual information but also access mental represe…
Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution
Gaspard Michel, Elena V. Epure, Romain Hennequin +1
Recent approaches to automatically detect the speaker of an utterance of direct speech often disregard general information about characters in favor of local information found in t…