Search papers, labs, and topics across Lattice.
Ubiquitous Knowledge Processing Lab (UKP Lab), Technical University of Darmstadt, National Research Center for Applied Cybersecurity ATHENE, Germany
6
0
8
17
ProReviewer outperforms larger models by up to 39% in peer review quality by enabling proactive investigation of research papers.
Contextual prompts can significantly boost stance detection accuracy, but only if the right type of context is chosen鈥擫LM-generated descriptions shine while user metadata may backfire.
Structural differences in circuits may be misleading, as they often reflect interchangeable mechanisms rather than distinct functionalities.
Current code reward models are myopic, mostly rewarding functional correctness, but Themis-RM learns to score code across multiple criteria and languages, opening the door to more nuanced and useful code generation.
Forget tedious multi-turn dialogues: Co-FactChecker's "trace-editing" lets human experts directly shape an LLM's reasoning process, leading to higher quality claim verification.
Most scientific claims in NLP die in obscurity, and even the survivors are more likely to be subtly reshaped than outright validated or debunked.
