FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models (2026)
FineSteer targets a familiar tension in inference-time steering of LLMs, which is used to reduce problems like jailbreak susceptibility and hallucination.
Learning to Think on Hypergraph: HyperCoT for Structure-Guided N-ary Knowledge Graph Completion (2026)
The paper addresses n-ary knowledge graph completion. The task is to predict a missing entity in a fact that links several entities, each filling a distinct semantic role. Such a fact is a hyperedge in a knowledge hypergraph. The authors identify two gaps. Embedding and GNN hypergraph models score hyperedges locally…
RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026)
This paper examines how vulnerable retrieval-augmented QA systems are to corpus poisoning. In this attack, someone plants crafted documents in the retrieval database so the system gives a chosen false answer. Earlier white-box attacks need gradients or internal details, which modern pipelines (hybrid search…

Co-authors here

4 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Updated 2 November 2026