collaborators

9 papers

cs.HC2026

Spatial Visual Analytics for Multi-Document Summary Verification

Jiahao Xu, Wei Liu, Yang Liu +5

Large language models increasingly generate summaries from collections of documents to support sensemaking and reporting, but verifying whether summary statements are grounded in s…

cs.HC2026

Scalable Semantic Steering of Embedding Projections

Wei Liu, Eric Krokos, Kirsten Whitley +2

Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with analyst-defined semantic relation…

cs.CL2026

From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing

Wei Liu, Hongkai Liu, Zhiying Deng +2

LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple pr…

cs.CL2026

The Cylindrical Representation Hypothesis for Language Model Steering

Lang Gao, Jinghui Zhang, Wei Liu +7

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based o…

cs.HC2026

LLM-Augmented Semantic Steering of Text Embedding Projection Spaces

Wei Liu, Eric Krokos, Kirsten Whitley +2

Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the relationships an analyst intends…

cs.CR2026

Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence

Huining Cui, Wei Liu

Retrieval-augmented generation (RAG) improves factual grounding by conditioning large language models on retrieved evidence, but it also opens a data-layer attack surface: poisoned…