6 papers · 1 filter
CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants
Xuzhao Geng, Haozhao Wang, Xuelian Li +4
Target-oriented dialogue systems have demonstrated strong capabilities in completing user goals through interactive conversations. However, existing studies are primarily designed…
Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
Yihao Ouyang, Shiwei Li, Haozhao Wang +6
Low-rank adaptation (LoRA) approximates the update of a pretrained weight matrix using the product of two low-rank matrices. However, standard LoRA follows an explicit-rank paradig…
Are We Evaluating the Edit Locality of LLM Model Editing Properly?
Wei Liu, Haomei Xu, Hongkai Liu +5
Model editing has recently emerged as a popular paradigm for efficiently updating knowledge in LLMs. A central desideratum of updating knowledge is to balance editing efficacy, i.e…
Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation
Wei Liu, Haomei Xu, Bingqing Liu +6
Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issu…
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
Wei Liu, Zhongyu Niu, Lang Gao +4
This study investigates the self-rationalization framework constructed with a cooperative game, where a generator initially extracts the most informative segment from raw input, an…
Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
Wei Liu, Zhiying Deng, Zhongyu Niu +4
Extracting a small subset of crucial rationales from the full input is a key problem in explainability research. The most widely used fundamental criterion for rationale extraction…