32 citations · 122 across the 14 of their papers we have counts for
14 papers
CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan +30
Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking pract…
Aspect Extraction from E-Commerce Product and Service Reviews
Valiant Lance D. Dionela, Fatima Kriselle S. Dy, Robin James M. Hombrebueno +3
Aspect Extraction (AE) is a key task in Aspect-Based Sentiment Analysis (ABSA), yet it remains difficult to apply in low-resource and code-switched contexts like Taglish, a mix of…
Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
Kriz Tahimic, Charibeth Cheng
As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mecha…
From Unstructured to Structured: Transforming Chatbot Dialogues into Data Mart Schema for Visualization
Mark Edward M. Gonzales, Elyssia Barrie H. Ong, Charibeth K. Cheng +2
Schools are among the primary avenues for public healthcare interventions. With resource limitations posing challenges to the routine conduct of health and wellness checks in Phili…
Using Synthetic Data for Conversational Response Generation in Low-resource Settings
Gabriel Louis Tan, Adrian Paule Ty, Schuyler Ng +3
Response generation is a task in natural language processing (NLP) where a model is trained to respond to human statements. Conversational response generators take this one step fu…
Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings
Dan John Velasco, Axel Alba, Trisha Gail Pelagio +5
Wordnets are indispensable tools for various natural language processing applications. Unfortunately, wordnets get outdated, and producing or updating wordnets can be slow and cost…