Timothy Baldwin

Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks

Don't Ignore the Tail: Decoupling top-$K$ Probabilities for Efficient Language Model Distillation

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory, and Test Time Compute Scaling

Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads

Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs

ToolGen: Unified Tool Retrieval and Calling via Generation