← Search

H. Jagadish

2 accepted papers

2024

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

ACL 2024findings

Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time methods steer LLM representations toward the “truthful directions” previously learned for truth elicitation. However, ap…