6 papers indexed here
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.
Experiments show that the proposed Preference Vector framework improves helpfulness without excessive conservatism, allows smooth control over preference trade-offs, and supports scalable multi-preference alignment.
SVF is proposed, which learns a differentiable concept scoring function whose local gradient defines the steering direction at each activation, making interventions explicitly context-dependent and enables efficient long-form and multi-attribute control within a unified framework.
TRACES is a representation-based proactive auditor that learns prefix-level trajectory risk states from the hidden representations of an observer LLM, and it is suggested that these risk states can help train a safer agent, highlighting the broader potential of proactive auditing for long-horizon agent safety.
In-context learning (ICL) enables models to infer tasks from demonstrations, but existing benchmarks generally lack matched text and image versions needed to compare ICL performance across modalities. We introduce TwinICL, a procedurally generated benchmark providing such pairs for controlled comparison. Across six ope...
This work introduces ConstructCIE, a manually annotated dataset for Causal Information Extraction from OSHA construction accident reports, and evaluates supervised sequence taggers and instruction-tuned LLMs in an end-to-end hierarchical extraction setting.
PEPPER (PErcePtion-Guided PERturbation), a backdoor defense that rewrites the caption into a semantically distant yet visually similar caption while adding unobtrusive elements, achieves enhanced robustness without training or access to model weights.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
