11 papers · 1 filter
LatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents
Jingyue Cong, Estrid He, Zhuang Li +5
Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local risks, overlooking failures wh…
Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models
Jingyue Cong, Andy Song, Yang Yu +7
Machine unlearning for large language models seeks to remove specified knowledge while preserving general capability, yet current methods often treat an entire response as the unit…
The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining
Vy Nguyen, Ziqi Xu, Jeffrey Chan +5
Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to answer reliably. A large body of…
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
Ahmed Sohair Khan, Estrid He, Chenglong Ma +2
Sensitive attributes such as age, income, and occupation can be inferred from user-generated content by aggregating indirect cues across many ordinary posts. LLM-based profilers ca…
I Am No One: Style-Aware Paraphrasing for Text Anonymization
Ahmed Sohair Khan, Estrid He, Monica Wachowicz +1
Authorship attribution models can re-identify users from seemingly anonymized text by exploiting stable stylistic fingerprints, even after explicit identifiers are removed, posing…
A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks
Du Yin, Xiachong Lin, Yue Tan +4
Traffic forecasting is important for efficient traffic management and route planning in smart cities. Existing traffic forecasting studies typically assume fixed sensor graphs, ove…
Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning
Vy Nguyen, Ziqi Xu, Jeffrey Chan +5
Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirable that models abstain rathe…
Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds
Waqas Khan, Tabinda Sarwar, Jingyue Cong +2
Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes reques…
Position Bias Undermines Preference Consistency in Listwise LLM-Based Reranking
Ethan Bito, Yongli Ren, Estrid He
Large language models (LLMs) have emerged as promising listwise rerankers for recommender systems, but their reliability under equivalent candidate permutations remains unclear. Si…
StrideDiffusion: Accelerating Diffusion Models for Time-series Generation
Du Yin, Estrid He, Julián Jerónimo Bañuelos +6
Diffusion models have become competitive generators for time series, but their practical use is limited by the large number of sequential denoising steps required at inference time…
One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation
Ethan Bito, Yongli Ren, Estrid He
Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candidates are presented. This crea…