AI chatbot platforms have become one of the most popular web interfaces users interact with online, routinely receiving personal and intimate information shared under an…AI chatbot platforms have become one of the most popular web interfaces users interact with online, routinely receiving personal and intimate information shared under an expectation of privacy.
Direct Preference Optimization (DPO) typically relies on preference pairs generated from diverse model pools and ranked by an external LLM judge.Direct Preference Optimization (DPO) typically relies on preference pairs generated from diverse model pools and ranked by an external LLM judge.
LLM agents increasingly interact with other agents on behalf of users, yet how users in the loop affect their agents' behavior–for better or worse–remains poorly…LLM agents increasingly interact with other agents on behalf of users, yet how users in the loop affect their agents' behavior–for better or worse–remains poorly understood.
Typed decision models return a probability distribution over options supplied by the caller, and software tends to act on that number as if it were a guarantee.Typed decision models return a probability distribution over options supplied by the caller, and software tends to act on that number as if it were a guarantee.
Early stopping promises to reduce compute costs for autonomous coding agents by terminating unpromising runs early.Early stopping promises to reduce compute costs for autonomous coding agents by terminating unpromising runs early. Deciding when to abandon a run requires separating baseline issue difficulty from the trajectory of an individual…
Nine years after learned indexes were proposed, their advantage on read-mostly data is well established, and a standard benchmark rates their best concurrent version as…Nine years after learned indexes were proposed, their advantage on read-mostly data is well established, and a standard benchmark rates their best concurrent version as almost ready for use.
LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors.LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors. We test this assumption against a minimal adversary.
Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models additional steps to compute before answering.Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models additional steps to compute before answering. It remains unclear what computation these steps actually perform.
Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that…Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that consistency can serve as a proxy for correctness when…
Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards.Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with verifiable rewards.
Schwarzschild A, Thakkar O, Ghalebikesabi S et al.
Canaries, or synthetic training records containing known secrets, are widely used to assess whether language models reveal information from their training data.Canaries, or synthetic training records containing known secrets, are widely used to assess whether language models reveal information from their training data. But how much do these measurements depend on the canaries themselves?
Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's personal…Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's personal agent negotiating with an enterprise's seller agent.