9 citations · 42 across the 36 of their papers we have counts for
36 papers
Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning
Xiaoxue Han, Libo Zhang, Zining Zhu +1
We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each c…
The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models
Yan Wang, Yitao Xu, Nanhan Shen +3
Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a pos…
Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts
Samaksh Bhargav, Zining Zhu
Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this req…
KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning
Zhendong Mi, Qitao Tan, Xiaodong Yu +3
Large language models (LLMs) have demonstrated impressive capabilities across numerous NLP tasks. Nevertheless, conventional first-order fine-tuning techniques impose heavy memory…
Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce
Haojin Wang, Zining Zhu, Freda Shi
Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt. In this work, we attempt to systematically understand…
Contrastive Similarity Learning for Market Forecasting: The ContraSim Framework
Nicholas Vinden, Raeid Saqur, Zining Zhu +1
We introduce the Contrastive Similarity Space Embedding Algorithm (ContraSim), a novel framework for uncovering the global semantic relationships between daily financial headlines…
INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent
Haohang Li, Yupeng Cao, Yangyang Yu +12
Recent advancements have underscored the potential of large language model (LLM)-based agents in financial decision-making. Despite this progress, the field currently encounters tw…
Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs
Brandon Jaipersaud, Zining Zhu, Frank Rudzicz +1
Tools for analyzing character portrayal in fiction are valuable for writers and literary scholars in developing and interpreting compelling stories. Existing tools, such as visuali…
What Would You Ask When You First Saw ? Evaluating LLM on Curiosity-Driven Questioning
Shashidhar Reddy Javaji, Zining Zhu
Large language models (LLMs) can store a massive amount of knowledge, yet their potential to acquire new knowledge remains unknown. We propose a novel evaluation framework that eva…
Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
Lei Yu, Jingcheng Niu, Zining Zhu +2
In this paper, we introduce DiscoGP, a novel framework for extracting self-contained modular units, or sheaves, within neural language models (LMs). Sheaves extend the concept of f…
Scenarios and Approaches for Situated Natural Language Explanations
Pengshuo Qiu, Frank Rudzicz, Zining Zhu
Large language models (LLMs) can be used to generate natural language explanations (NLE) that are adapted to different users' situations. However, there is yet to be a quantitative…
How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?
Huaizhi Ge, Frank Rudzicz, Zining Zhu
Large language models (LLMs) have demonstrated remarkable capabilities, but updating their knowledge post-training remains a critical challenge. While recent model editing techniqu…
Understanding Language Model Circuits through Knowledge Editing
Huaizhi Ge, Frank Rudzicz, Zining Zhu
Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these cruci…
ACCORD: Closing the Commonsense Measurability Gap
François Roewer-Després, Jinyue Feng, Zining Zhu +1
We present ACCORD, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop…
What does the Knowledge Neuron Thesis Have to do with Knowledge?
Jingcheng Niu, Andrew Liu, Zining Zhu +1
We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascen…
LLM-Generated Black-box Explanations Can Be Adversarially Helpful
Rohan Ajwani, Shashidhar Reddy Javaji, Frank Rudzicz +1
Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations,…
Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation
Rohan Deepak Ajwani, Zining Zhu, Jonathan Rose +1
Transformer-based Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts. However, controlling the direction of gene…
A State-Vector Framework for Dataset Effects
Esmat Sahak, Zining Zhu, Frank Rudzicz
The impressive success of recent deep neural network (DNN)-based systems is significantly influenced by the high-quality datasets used in training. However, the effects of the data…
Measuring Information in Text Explanations
Zining Zhu, Frank Rudzicz
Text-based explanation is a particularly promising approach in explainable AI, but the evaluation of text explanations is method-dependent. We argue that placing the explanations o…
Situated Natural Language Explanations
Zining Zhu, Haoming Jiang, Jingfeng Yang +6
Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to genera…
CCGen: Explainable Complementary Concept Generation in E-Commerce
Jie Huang, Yifan Gao, Zheng Li +7
We propose and study Complementary Concept Generation (CCGen): given a concept of interest, e.g., "Digital Cameras", generating a list of complementary concepts, e.g., 1) Camera Le…
Predicting Fine-Tuning Performance with Probing
Zining Zhu, Soroosh Shahtalebi, Frank Rudzicz
Large NLP models have recently shown impressive performance in language understanding tasks, typically evaluated by their fine-tuned performance. Alternatively, probing has receive…
OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization
Zining Zhu, Soroosh Shahtalebi, Frank Rudzicz
The ability to generalize out-of-domain (OOD) is an important goal for deep neural network development, and researchers have proposed many high-performing OOD generalization method…
On the data requirements of probing
Zining Zhu, Jixuan Wang, Bai Li +1
As large and powerful neural language models are developed, researchers have been increasingly interested in developing diagnostic tools to probe them. There are many papers with c…