6 papers
Speak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language Models
Yang Liu, Masahiro Kaneko, Chenhui Chu
Recent work reports that the distribution verbalized directly in the output text aligns far better with human opinion distributions than the next-token log-probability distribution…
Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue
Yihang Li, Chenhui Chu
The Neural Finite State Machine (NFSM) framework offers a pragmatic path to full-duplex dialogue by serializing turn-taking control and response generation onto a single causal tap…
Understanding the Prompt Sensitivity
Yang Liu, Chenhui Chu
Prompt sensitivity, which refers to how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt, raises concerns among users about the…
Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation
Yihang Li, Chenhui Chu
Evaluating meeting effectiveness is crucial for improving organizational productivity. Current approaches rely on post-hoc surveys that yield a single coarse-grained score for an e…
Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs
Yang Liu, Chenhui Chu
Large language models (LLMs) can lead to undesired consequences when misaligned with human values, especially in scenarios involving complex and sensitive social biases. Previous s…
On the Alignment of Large Language Models with Global Human Opinion
Yang Liu, Masahiro Kaneko, Chenhui Chu
Today's large language models (LLMs) are capable of supporting multilingual scenarios, allowing users to interact with LLMs in their native languages. When LLMs respond to subjecti…