Papers by Daniel Silva

2 papers
A Brief Survey of Textual Dialogue Corpora (2022.lrec-1)

Copied to clipboard

Challenge: Several dialogue corpora are available for research purposes, but they do not cover all the necessities of real-world applications.
Approach: They analyze available dialogue corpora and propose possible approaches to create new ones.
Outcome: The proposed corpus of human-human dialogues is based on a list of available dialogue corpora . it covers speakers, size, languages, collection, annotations, and domains . some trends are identified and possible approaches are also discussed .
Look Who’s Talking Now: Covert Channels From Biased LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: steganography encodes hidden messages into model-generated tokens . tradeoff between how much hidden information can be introduced and how much the model can be perturbed is important .
Approach: They propose to use large language model-based steganography to encode hidden messages into model-generated tokens.
Outcome: The proposed techniques are nearly optimal under a practical but difficult set of constraints . the proposed techniques ensure that only someone with the appropriate decoding key can access the hidden information .

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