English
Related papers

Related papers: Conceptor-Aided Debiasing of Large Language Models

200 papers

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent studies have identified various biases that such models exhibit and have proposed methods to correct these biases. However, most of the works address a…

Computation and Language · Computer Science 2024-02-13 Prachi Jain , Ashutosh Sathe , Varun Gumma , Kabir Ahuja , Sunayana Sitaram

In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. We discover that LLM's performance exceeds humans and surpasses the…

Computation and Language · Computer Science 2024-06-05 Xinyi Liu , Pinxin Liu , Hangfeng He

Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in…

Computation and Language · Computer Science 2021-03-19 Daniel Loureiro , Kiamehr Rezaee , Mohammad Taher Pilehvar , Jose Camacho-Collados

Large Language Models (LLMs) have significantly advanced natural language processing applications, yet their widespread use raises concerns regarding inherent biases that may reduce utility or harm for particular social groups. Despite the…

Computers and Society · Computer Science 2025-02-05 Bo Pang , Tingrui Qiao , Caroline Walker , Chris Cunningham , Yun Sing Koh

Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been…

Social and Information Networks · Computer Science 2021-01-27 Marzieh Mozafari , Reza Farahbakhsh , Noel Crespi

Recent advancements in large language models (LLMs) have enabled their widespread use across diverse real-world applications. However, concerns remain about their tendency to encode and reproduce ideological biases along political and…

Computation and Language · Computer Science 2025-09-23 Afrozah Nadeem , Mark Dras , Usman Naseem

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is…

Computation and Language · Computer Science 2020-11-17 Md Tahmid Rahman Laskar , Enamul Hoque , Jimmy Xiangji Huang

Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities as their scale expands to billions of parameters. Deploying these large-scale models on resource-constrained platforms presents significant…

Hardware Architecture · Computer Science 2025-05-15 Keran Zheng , Yinting Huang , Zhewen Yu , Christos-Savvas Bouganis

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

Computation and Language · Computer Science 2020-05-11 Xing Wu , Yibing Liu , Xiangyang Zhou , Dianhai Yu

Debiasing techniques such as SentDebias aim to reduce bias in large language models (LLMs). Previous studies have evaluated their cross-lingual transferability by directly applying these methods to LLM representations, revealing their…

Computation and Language · Computer Science 2025-08-26 Qiwei Peng , Guimin Hu , Yekun Chai , Anders Søgaard

The pseudo-projector is a lightweight modification that can be integrated into existing language models and other neural networks without altering their core architecture. It can be viewed as a hidden-representation corrector that reduces…

Machine Learning · Computer Science 2026-03-11 Vitaly Bulgakov

BERT-type structure has led to the revolution of vision-language pre-training and the achievement of state-of-the-art results on numerous vision-language downstream tasks. Existing solutions dominantly capitalize on the multi-modal inputs…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Jianjie Luo , Yehao Li , Yingwei Pan , Ting Yao , Hongyang Chao , Tao Mei

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Haozhe Zhao , Shuzheng Si , Liang Chen , Yichi Zhang , Maosong Sun , Mingjia Zhang , Baobao Chang

Large Language Models (LLMs) are trained on large corpora written by humans and demonstrate high performance on various tasks. However, as humans are susceptible to cognitive biases, which can result in irrational judgments, LLMs can also…

Computation and Language · Computer Science 2024-12-03 Yasuaki Sumita , Koh Takeuchi , Hisashi Kashima

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

One of the main methods for computational interpretation of a text is mapping it into a vector in some embedding space. Such vectors can then be used for a variety of textual processing tasks. Recently, most embedding spaces are a product…

Computation and Language · Computer Science 2023-11-10 Adi Simhi , Shaul Markovitch

Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…

Computation and Language · Computer Science 2023-05-18 Na Li , Hanane Kteich , Zied Bouraoui , Steven Schockaert

This paper assesses the ability of large language models (LLMs) to translate texts that include inter-sentential dependencies. We use the English-French DiscEvalMT benchmark (Bawden et al., 2018) with pairs of sentences containing…

Computation and Language · Computer Science 2026-03-09 Shabnam Ataee , Hugo Huart , Andrei Popescu-Belis