Papers by Antoine Chaffin

3 papers
PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding (2022.naacl-main)

Copied to clipboard

Challenge: Large language models (LM) based on transformers generate plausible long texts . a discriminator-guided approach allows to apply constraints more finely and dynamically.
Approach: They propose to use a discriminator-guided approach to generate constrained texts without fine-tuning the LM.
Outcome: The proposed method is easier and cheaper to train than fine-tuning the LM.
Generating Artificial Texts as Substitution or Complement of Training Data (2022.lrec-1)

Copied to clipboard

Challenge: Existing approaches to generate text for supervised learning tasks use transformers to generate learning data.
Approach: They propose to use transformers to generate supervised learning data for supervised machine learning tasks and propose to train a neural language model trained on the original training texts.
Outcome: The proposed models can be used in a certain extend but require pre-processing to significantly improve performance.
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference (2025.acl-long)

Copied to clipboard

Challenge: Encoder-only transformer models such as BERT offer a great performance-size tradeoff for retrieval and classification tasks compared to larger decoder models.
Approach: They introduce a new transformer model, ModernBERT, which brings modern model optimizations to encoder-only transformer models.
Outcome: The proposed model improves on the BERT transformer model and is faster and more memory efficient than the older models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations