3 papers
cs.CL2026
Consistency Training while Mitigating Obfuscation via Rate Matching
Sohaib Imran, Prakhar Gupta, Jannes Elstner +1
Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer. Consistency training reduces this influence by training m…
cs.CL2025
Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data
Sohaib Imran, Rob Lamb, Peter M. Atkinson
Large language models (LLMs) are trained on large corpora, yet it is unclear whether they can reason about the information present within their training data. We design experiments…
cs.CL2025
Are LLM Belief Updates Consistent with Bayes' Theorem?
Sohaib Imran, Ihor Kendiukhov, Matthew Broerman +4
Do larger and more capable language models learn to update their "beliefs" about propositions more consistently with Bayes' theorem when presented with evidence in-context? To test…