9 citations · 42 across the 36 of their papers we have counts for
25 papers · 1 filter
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…
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…
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…
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…
Neural reality of argument structure constructions
Bai Li, Zining Zhu, Guillaume Thomas +2
In lexicalist linguistic theories, argument structure is assumed to be predictable from the meaning of verbs. As a result, the verb is the primary determinant of the meaning of a c…
Quantifying the Task-Specific Information in Text-Based Classifications
Zining Zhu, Aparna Balagopalan, Marzyeh Ghassemi +1
Recently, neural natural language models have attained state-of-the-art performance on a wide variety of tasks, but the high performance can result from superficial, surface-level…
An unsupervised framework for tracing textual sources of moral change
Aida Ramezani, Zining Zhu, Frank Rudzicz +1
Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time. Recent advances in natural language processing have shown…
What do writing features tell us about AI papers?
Zining Zhu, Bai Li, Yang Xu +1
As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increas…
How is BERT surprised? Layerwise detection of linguistic anomalies
Bai Li, Zining Zhu, Guillaume Thomas +2
Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomal…
Semantic coordinates analysis reveals language changes in the AI field
Zining Zhu, Yang Xu, Frank Rudzicz
Semantic shifts can reflect changes in beliefs across hundreds of years, but it is less clear whether trends in fast-changing communities across a short time can be detected. We pr…
Examining the rhetorical capacities of neural language models
Zining Zhu, Chuer Pan, Mohamed Abdalla +1
Recently, neural language models (LMs) have demonstrated impressive abilities in generating high-quality discourse. While many recent papers have analyzed the syntactic aspects enc…
An information theoretic view on selecting linguistic probes
Zining Zhu, Frank Rudzicz
There is increasing interest in assessing the linguistic knowledge encoded in neural representations. A popular approach is to attach a diagnostic classifier -- or "probe" -- to pe…