2.4k citations · 7.9k across the 182 of their papers we have counts for
29 papers · 1 filter
Why Retrieval-Augmented Generation Fails: A Graph Perspective
Kai Guo, Xinnan Dai, Zhibo Zhang +5
Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in retrieved evidence. However, RAG…
Retrieval Heads are Dynamic
Yuping Lin, Zitao Li, Yue Xing +6
Recent studies have identified "retrieval heads" in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on st…
Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
Hang Li, Kaiqi Yang, Yucheng Chu +2
Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or…
Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path
Xinnan Dai, Qihao Wen, Yifei Shen +4
Large Language Models (LLMs) have achieved great success in various reasoning tasks. In this work, we focus on the graph reasoning ability of LLMs. Although theoretical studies pro…
Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
Guangliang Liu, Haitao Mao, Jiliang Tang +1
Large Language Models (LLMs) are capable of producing content that perpetuates stereotypes, discrimination, and toxicity. The recently proposed moral self-correction is a computati…
Knowledge Tagging System on Math Questions via LLMs with Flexible Demonstration Retriever
Hang Li, Tianlong Xu, Jiliang Tang +1
Knowledge tagging for questions plays a crucial role in contemporary intelligent educational applications, including learning progress diagnosis, practice question recommendations,…
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
Yuping Lin, Pengfei He, Han Xu +4
Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack…
On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
Guangliang Liu, Haitao Mao, Bochuan Cao +5
Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only the task's goal wit…
Large Language Models for Education: A Survey and Outlook
Shen Wang, Tianlong Xu, Hang Li +5
The advent of Large Language Models (LLMs) has brought in a new era of possibilities in the realm of education. This survey paper summarizes the various technologies of LLMs in edu…
Automate Knowledge Concept Tagging on Math Questions with LLMs
Hang Li, Tianlong Xu, Jiliang Tang +1
Knowledge concept tagging for questions plays a crucial role in contemporary intelligent educational applications, including learning progress diagnosis, practice question recommen…
A Survey to Recent Progress Towards Understanding In-Context Learning
Haitao Mao, Guangliang Liu, Yao Ma +3
In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the…
TrustLLM: Trustworthiness in Large Language Models
Yue Huang, Lichao Sun, Haoran Wang +67
Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs prese…
On the Generalization of Training-based ChatGPT Detection Methods
Han Xu, Jie Ren, Pengfei He +5
ChatGPT is one of the most popular language models which achieve amazing performance on various natural language tasks. Consequently, there is also an urgent need to detect the tex…
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective
Jiatong Li, Yunqing Liu, Wenqi Fan +4
Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs. However, most of the existing methods heavily rely on do…
Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals
Jamell Dacon, Harry Shomer, Shaylynn Crum-Dacon +1
Online discussions, panels, talk page edits, etc., often contain harmful conversational content i.e., hate speech, death threats and offensive language, especially towards certain…
What Truly Matters? Using Linguistic Cues for Analyzing the #BlackLivesMatter Movement and its Counter Protests: 2013 to 2020
Jamell Dacon, Jiliang Tang
Since the fatal shooting of 17-year old Black teenager Trayvon Martin in February 2012 by a White neighborhood watchman, George Zimmerman in Sanford, Florida, there has been a sign…
Solving ESL Sentence Completion Questions via Pre-trained Neural Language Models
Qiongqiong Liu, Tianqiao Liu, Jiafu Zhao +6
Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options. SC questions are widely…
Multi-Task Learning based Online Dialogic Instruction Detection with Pre-trained Language Models
Yang Hao, Hang Li, Wenbiao Ding +4
In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective st…
The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification
Haochen Liu, Wei Jin, Hamid Karimi +2
It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity ter…
Personalized Multimodal Feedback Generation in Education
Haochen Liu, Zitao Liu, Zhongqin Wu +1
The automatic evaluation for school assignments is an important application of AI in the education field. In this work, we focus on the task of personalized multimodal feedback gen…
Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning
Haochen Liu, Wentao Wang, Yiqi Wang +3
Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation da…
Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
Haochen Liu, Zhiwei Wang, Tyler Derr +1
Recently, neural network based dialogue systems have become ubiquitous in our increasingly digitalized society. However, due to their inherent opaqueness, some recently raised conc…
Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms
Gale Yan Huang, Jiahao Chen, Haochen Liu +6
Asking questions is one of the most crucial pedagogical techniques used by teachers in class. It not only offers open-ended discussions between teachers and students to exchange id…
Learning Multi-level Dependencies for Robust Word Recognition
Zhiwei Wang, Hui Liu, Jiliang Tang +3
Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken…