62 citations · 119 across the 26 of their papers we have counts for
19 papers · 1 filter
Beyond Belief: Evaluating and Mitigating LLM Susceptibility to Misinformation
Emran Kanaan, Jiho Lee, Ibrahim Odat +2
Tool-using large language models (LLMs) must decide whether external information warrants action. We investigate whether their expressed credibility judgments reliably indicate beh…
When Linguistic and Internal Confidence Diverge in Large Language Models
Hefan Zhang, Bingquan Zhang, Ming Cheng +3
Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's internal confidence. We study…
When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation
Yahan Zheng, John Guerrerio, Soroush Vosoughi +1
Preprocessing-based methods for stereotype mitigation, such as pre-/post-training on debiased corpora, are widely used in NLP. While these approaches reduce measurable stereotypes…
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Weicheng Ma, John Guerrerio, Soroush Vosoughi
Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages and the high cost of manual…
A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling
Shiyu Ji, Farnoosh Hashemi, Joice Chen +9
Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been li…
Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication
Weicheng Ma, Hefan Zhang, Ivory Yang +8
Large Language Models (LLMs) have shown proficiency in generating persuasive dialogue, yet concerns about the fluency and sophistication of their outputs persist. This paper presen…
Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages
Ivory Yang, Weicheng Ma, Chunhui Zhang +1
Endangered languages, such as Navajo - the most widely spoken Native American language - are significantly underrepresented in contemporary language technologies, exacerbating the…
NushuRescue: Revitalization of the Endangered Nushu Language with AI
Ivory Yang, Weicheng Ma, Soroush Vosoughi
The preservation and revitalization of endangered and extinct languages is a meaningful endeavor, conserving cultural heritage while enriching fields like linguistics and anthropol…
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
Lin Shi, Chiyu Ma, Wenhua Liang +3
LLM-as-a-Judge has emerged as a promising alternative to human evaluators across various tasks, yet inherent biases - particularly position bias, the tendency to favor solutions ba…
Capturing Topic Framing via Masked Language Modeling
Xiaobo Guo, Weicheng Ma, Soroush Vosoughi
Differential framing of issues can lead to divergent world views on important issues. This is especially true in domains where the information presented can reach a large audience,…
EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English
Weicheng Ma, Samiha Datta, Lili Wang +1
While cultural backgrounds have been shown to affect linguistic expressions, existing natural language processing (NLP) research on culture modeling is overly coarse-grained and do…
Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
Weicheng Ma, Kai Zhang, Renze Lou +2
This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has…
BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
Aadil Islam, Weicheng Ma, Soroush Vosoughi
This paper describes a system submitted by team BigGreen to LCP 2021 for predicting the lexical complexity of English words in a given context. We assemble a feature engineering-ba…
Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
Yakoob Khan, Weicheng Ma, Soroush Vosoughi
This paper describes our approach to the Toxic Spans Detection problem (SemEval-2021 Task 5). We propose BERToxic, a system that fine-tunes a pre-trained BERT model to locate toxic…
Improvements and Extensions on Metaphor Detection
Weicheng Ma, Ruibo Liu, Lili Wang +1
Metaphors are ubiquitous in human language. The metaphor detection task (MD) aims at detecting and interpreting metaphors from written language, which is crucial in natural languag…
An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data
Lili Wang, Chongyang Gao, Jason Wei +3
The field of NLP has seen unprecedented achievements in recent years. Most notably, with the advent of large-scale pre-trained Transformer-based language models, such as BERT, ther…
Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
Ruibo Liu, Guangxuan Xu, Chenyan Jia +3
Data augmentation is proven to be effective in many NLU tasks, especially for those suffering from data scarcity. In this paper, we present a powerful and easy to deploy text augme…
Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding
Weicheng Ma, Ruibo Liu, Lili Wang +1
Authorship identification tasks, which rely heavily on linguistic styles, have always been an important part of Natural Language Understanding (NLU) research. While other tasks bas…
Emoji Prediction: Extensions and Benchmarking
Weicheng Ma, Ruibo Liu, Lili Wang +1
Emojis are a succinct form of language which can express concrete meanings, emotions, and intentions. Emojis also carry signals that can be used to better understand communicative…