Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Truth-value judgment in language models: 'truth directions' are context sensitive
Stefan F. Schouten, Peter Bloem, Ilia Markov +1
Recent work has demonstrated that the latent spaces of large language models (LLMs) contain directions predictive of the truth of sentences. Multiple methods recover such direction…
cs.CL2023
Reasoning about Ambiguous Definite Descriptions
Stefan F. Schouten, Peter Bloem, Ilia Markov +1
Natural language reasoning plays an increasingly important role in improving language models' ability to solve complex language understanding tasks. An interesting use case for rea…