4 citations · 11 across the 14 of their papers we have counts for
14 papers
HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning
Yujian Liu, Jiabao Ji, Yang Zhang +3
Existing LLM-based automatic test generation methods mainly produce input and expected output pairs to categorize the intended behavior of correct programs. Although straightforwar…
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking
Li An, Yujian Liu, Yepeng Liu +3
Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construc…
Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
Li An, Yujian Liu, Yepeng Liu +3
Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the waterm…
Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
Yujian Liu, Shiyu Chang, Tommi Jaakkola +1
Recent studies have identified one aggravating factor of LLM hallucinations as the knowledge inconsistency between pre-training and fine-tuning, where unfamiliar fine-tuning data m…
VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs
Qiucheng Wu, Handong Zhao, Michael Saxon +4
Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the…
Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
Yujian Liu, Yang Zhang, Tommi Jaakkola +1
This paper investigates Who's Harry Potter (WHP), a pioneering yet insufficiently understood method for LLM unlearning. We explore it in two steps. First, we introduce a new task o…
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
Jiabao Ji, Yujian Liu, Yang Zhang +4
As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of L…
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation
Bairu Hou, Yang Zhang, Jacob Andreas +1
This paper focuses on the task of hallucination detection, which aims to determine the truthfulness of LLM-generated statements. To address this problem, a popular class of methods…
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Jiabao Ji, Bairu Hou, Zhen Zhang +7
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerab…
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Jiabao Ji, Bairu Hou, Alexander Robey +5
Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While…
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion
Yujian Liu, Jiabao Ji, Tong Yu +6
Table question answering is a popular task that assesses a model's ability to understand and interact with structured data. However, the given table often does not contain sufficie…
Correcting Diffusion Generation through Resampling
Yujian Liu, Yang Zhang, Tommi Jaakkola +1
Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth image…
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
Bairu Hou, Yujian Liu, Kaizhi Qian +3
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the…
Audio-Visual Neural Syntax Acquisition
Cheng-I Jeff Lai, Freda Shi, Puyuan Peng +10
We study phrase structure induction from visually-grounded speech. The core idea is to first segment the speech waveform into sequences of word segments, and subsequently induce ph…