5 papers
When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
Siddharth Chauhan, Thomas Butler, Abhishek Singhania +2
The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argum…
Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
Yuefeng Peng, Parnian Afshar, Megan Ganji +4
Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged a…
DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
Jio Oh, Paul Vicinanza, Thomas Butler +3
More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects and generate stereotyped responses…
English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training
Mehak Dhaliwal, Shashwat Chaurasia, Yao Qin +2
Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities acros…
PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection
Ali Lotfi Rezaabad, Bikram Khanal, Shashwat Chaurasia +5
Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. E…