Blog(4)

• A Class-Balanced Soft-Voting System for Detecting Multi-Generator Machine-Generated Text

  SemEval-2024 Task 8 provides a challenge to detect human-written and machine-generated text. There are 3 subtasks for different detection scenarios. This paper proposes a system that mainly deals with Subtask B.

• Towards LLM-Based Automatic Boundary Detection for Human-Machine Mixed Text

  Large Language Models (LLMs), particularly the debut of ChatGPT, have made significant advancement and demonstrated the ability to produce coherent and natural-sounding text across a wide range of applications.

• [INTERSPEECH 2024 Series #2] NL-ITI: Enhancing LLM Truthfulness Through Internal Modifications

  As AI becomes increasingly embedded in our daily lives, ensuring that these systems behave safely and align with our values and needs is crucial.

View More

Research Areas(0)

Publications(8)

• Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery

  AuthorCristina Cornelio

  PublishedInternational Conference on Intelligent Robots and Systems (IROS)

  Date2024-10-14

• Open-Source Conversational AI with SpeechBrain 1.0

  AuthorTitouan Parcollet, Shucong Zhang

  PublishedJournal of Machine Learning Research

  Date2024-09-09

• AlpaGasus: Training A Better Alpaca with Fewer Data

  AuthorKalpa Gunaratna,Zheng Tang,Vijay Srinivasan,Hongxia Jin

  PublishedInternational Conference on Learning Representations (ICLR)

  Date2024-05-07

View More

News(4)

• Celebrating Innovation and Collaboration Through Open Source at SOSCON PH 2024

  The Philippine tech community convened for another year of Samsung Open Source Conference Philippines (SOSCON PH) 2024 last October 12 at Novotel Manila. This year marked the third installment and second onsite conference of SOSCON PH, which traced its origins in South Korea back in 2014. This year, over 300 professionals, educators, and students attended the event, making this the biggest SOSCON PH thus far.

• [Blog] NL-ITI: Enhancing LLM Truthfulness Through Internal Modifications

  As AI becomes increasingly embedded in our daily lives, ensuring that these systems behave safely and align with our values and needs is crucial.

• [Blog] Towards LLM-Based Automatic Boundary Detection for Human-Machine Mixed Text

  Large Language Models (LLMs), particularly the debut of ChatGPT, have made significant advancement and demonstrated the ability to produce coherent and natural-sounding text across a wide range of applications. However, the proliferation of generated text has raised concerns regarding the potential for misuse of these LLMs.

View More

Others(0)