We have 7 of 28 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.
This work identifies a factual-salient layer span within LLMs whose derived signal is selectively elevated for factual tokens and exhibits anomalous spikes at hallucination-prone steps, and proposes DescaPE, a decoding framework that leverages internal model signals to suppress hallucination-prone trajectories at infer...
Experiments on three LRMs show that SaLT-DPO consistently reduces unsafe rates for both reasoning and answer segments while mitigating degradation in benign compliance and preserving general reasoning performance.
This work proposes a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking and demonstrates consistent improvements in retrieval quality and downstream QA performance over baselines.
Text-to-image safety guardrails fail to generalize equitably to non-standard dialects, formalized as the dialect penalty, where filters trigger based on linguistic surface features rather than semantic intent, and is mitigable via group-balanced retraining.
ALTSTEER is an inference-time framework that couples selective intervention with refusal-anchored constructive redirection within a single inference pass, and uses an internal refusal-relevant signal to decide when to steer, and applies staged steering to shift generation from refusal-oriented control toward constructi...
The introduction of CRiT-QA (Counterfactual Reasoning with Traps), a dataset explicitly designed to address both limitations of large language models' multi-hop reasoning, and provides a foundation for developing more reliable, evidence-grounded LLMs.
IterCOMP is proposed, a unified, training-free prompt compression framework that incorporates multi-hop reasoning within an iterative compression loop that achieves substantial improvements in Exact Match and F1 scores while reducing the token budget.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
