Search papers, labs, and topics across Lattice.
7
0
11
5
ODRA's innovative approach to modeling patient resistance leads to synthetic therapy sessions that are not only more realistic but also preferred by licensed psychologists.
Replacing just 12% of traditional training data with OctoLong's curated code contexts leads to substantial improvements in long-range retrieval and state tracking for language models.
Few features in sparse autoencoders provide consistent, reusable directions for model behavior, complicating interpretability efforts.
Human participation isn't just a stopgap for AI's shortcomings; it's a vital component in shaping outcomes that emerge through collaboration.
Risk-averse decision-making can backfire, leading to generic outputs, while Bayesian methods enhance LLM performance in high-stakes tasks like tutoring and peer review.
LLMs excel at capturing static affect in text, but modeling *changes* in affect benefits more from tracking recent affective trajectories than from analyzing textual semantics.
Synthetic counseling dialogues can be made significantly more realistic and useful for fine-tuning by grounding them in structured Client Psychological Graphs that capture the interplay of a client's thoughts, emotions, and behaviors.
