9 papers
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…
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…
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…
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…
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…
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…
Time-Interval-Aware Disentangled Expert Modeling for Next-Basket Recommendation
Zhiying Deng, Yuan Fu, Usman Farooq +3
Next-basket recommendation (NBR) is a type of recommendation that aims to predict a set of items a user will purchase based on their historical transaction basket sequences. It is…
When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
Lang Gao, Xuhui Li, Chenxi Wang +7
Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of…
Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
Lang Gao, Kaiyang Wan, Wei Liu +6
Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We focus on a common form of bias: when two reference concepts in the model's concept…