We have 5 of 27 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Large Language Model (LLM) assistants routinely decide whether they can trust users and third parties whose competence, intentions, and integrity they cannot verify. This uncertainty matters for safety, as trusting the wrong party can lead an agent to comply with harmful requests or act on malicious instructions encoun...
Locating relevant files from natural-language requests is a core subtask for agents operating over code repositories. We investigate whether this task can be delegated to compact, specialized models to enable on-device search while reducing the token usage, latency, and inference cost of larger agents. We show that sem...
Large Language Models fail at implicit multi-hop reasoning: a model answers"When was $X$ born?"and"Who is $Y$'s closest friend?"correctly but fails on"When was $Y$'s closest friend born?"in a single forward pass, even when both facts are perfectly memorized and individually retrievable. We study this failure in a contr...
These token-trigger mechanisms decompose into distinct SAE feature directions, with separate features for trigger detection, residual-stream propagation, and later language tracking, with this role-level decomposition most likely to transfer to other trigger-based backdoors, even when the payload, layers, or circuit lo...
It is found that large language models are strong on knowledge-intensive topics such as history, geography, and mathematics, but substantially weaker on everyday popular-culture topics such as celebrities, music, movies, and news.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
