For details, check her homepage.
Latest
- Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
- Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization
- When Models Reason in Your Language: Controlling Thinking Trace Language Comes at the Cost of Accuracy
- On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation
- Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation
- MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs
- Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models