7 papers
Conceptors for Semantic Steering
Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6
Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely un…
A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents
Young-Min Cho, Yuan Yuan, Sharath Chandra Guntuku +1
Style features such as friendly, helpful, or concise are widely used in prompts to steer the behavior of Large Language Model (LLM) conversational agents, yet their unintended side…
Culturally-Aware Conversations: A Framework & Benchmark for LLMs
Shreya Havaldar, Sunny Rai, Young-Min Cho +1
Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgroun…
Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarks
Aaron Xuxiang Tian, Ruofan Zhang, Jiayao Tang +12
We study multi-turn multi-agent orchestration, where multiple large language model (LLM) agents interact over multiple turns by iteratively proposing answers or casting votes until…
Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
Young-Min Cho, Sharath Chandra Guntuku, Lyle Ungar
Recent advancements in Large Language Models (LLMs) have enabled the emergence of multi-agent systems where LLMs interact, collaborate, and make decisions in shared environments. W…
Cross-Cultural Differences in Mental Health Expressions on Social Media
Sunny Rai, Khushi Shelat, Devansh R Jain +6
Culture moderates the way individuals perceive and express mental distress. Current understandings of mental health expressions on social media, however, are predominantly derived…