中文
相关论文

相关论文: Decoding Biases: Automated Methods and LLM Judges …

200 篇论文

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

计算与语言 · 计算机科学 2024-05-30 Tomasz Limisiewicz , David Mareček , Tomáš Musil

Large language models (LLMs) can generate persuasive narratives at scale, raising concerns about their potential use in disinformation campaigns. Assessing this risk ultimately requires understanding how readers receive such content. In…

人工智能 · 计算机科学 2026-04-09 Zonghuan Xu , Xiang Zheng , Yutao Wu , Xingjun Ma

Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to…

Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…

计算与语言 · 计算机科学 2025-03-11 Suvendu Mohanty

Large Language Models are increasingly employed in generating consumer product recommendations, yet their potential for embedding and amplifying gender and race biases remains underexplored. This paper serves as one of the first attempts to…

计算与语言 · 计算机科学 2026-02-10 Ke Xu , Shera Potka , Alex Thomo

Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves…

计算与语言 · 计算机科学 2025-11-26 Yixin Liu , Pengfei Liu , Arman Cohan

Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biases is essential for ensuring the reliability…

计算与语言 · 计算机科学 2026-03-10 Hongli Zhou , Hui Huang , Rui Zhang , Kehai Chen , Bing Xu , Conghui Zhu , Tiejun Zhao , Muyun Yang

Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. This…

计算与语言 · 计算机科学 2025-07-25 Yuen Chen , Vethavikashini Chithrra Raghuram , Justus Mattern , Rada Mihalcea , Zhijing Jin

The impressive performance of large language models (LLMs) has attracted considerable attention from the academic and industrial communities. Besides how to construct and train LLMs, how to effectively evaluate and compare the capacity of…

信息检索 · 计算机科学 2024-06-04 Zhumin Chu , Qingyao Ai , Yiteng Tu , Haitao Li , Yiqun Liu

Bias is a disproportionate prejudice in favor of one side against another. Due to the success of transformer-based Masked Language Models (MLMs) and their impact on many NLP tasks, a systematic evaluation of bias in these models is needed…

计算与语言 · 计算机科学 2024-04-11 Jeongrok Yu , Seong Ug Kim , Jacob Choi , Jinho D. Choi

Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm…

计算与语言 · 计算机科学 2024-03-14 Tharindu Kumarage , Amrita Bhattacharjee , Joshua Garland

Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to…

计算与语言 · 计算机科学 2025-01-07 Shaina Raza , Oluwanifemi Bamgbose , Shardul Ghuge , Fatemeh Tavakol , Deepak John Reji , Syed Raza Bashir

The emergence of Large Language Models (LLMs) as chat assistants capable of generating human-like conversations has amplified the need for robust evaluation methods, particularly for open-ended tasks. Conventional metrics such as EM and F1,…

计算与语言 · 计算机科学 2025-11-12 Sher Badshah , Hassan Sajjad

In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance.…

计算与语言 · 计算机科学 2024-06-13 Zhen Li , Xiaohan Xu , Tao Shen , Can Xu , Jia-Chen Gu , Yuxuan Lai , Chongyang Tao , Shuai Ma

The recent advances in large language models (LLMs) have revolutionized industries such as finance, marketing, and customer service by enabling sophisticated natural language processing tasks. However, the broad adoption of LLMs brings…

计算机与社会 · 计算机科学 2025-02-19 Berk Yilmaz , Huthaifa I. Ashqar

We are exposed to much information trying to influence us, such as teaser messages, debates, politically framed news, and propaganda - all of which use persuasive language. With the recent interest in Large Language Models (LLMs), we study…

计算与语言 · 计算机科学 2025-02-24 Amalie Brogaard Pauli , Isabelle Augenstein , Ira Assent

LLMs have emerged as a promising tool for assisting individuals in diverse text-generation tasks, including job-related texts. However, LLM-generated answers have been increasingly found to exhibit gender bias. This study evaluates three…

计算与语言 · 计算机科学 2024-12-02 Haein Kong , Yongsu Ahn , Sangyub Lee , Yunho Maeng

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM)…

计算与语言 · 计算机科学 2025-03-04 Lianghui Zhu , Xinggang Wang , Xinlong Wang

This paper presents a method to analyze the inference patterns used by Large Language Models (LLMs) for judgment in a case study on legal LLMs, so as to identify potential incorrect representations of the LLM, according to human domain…

人工智能 · 计算机科学 2025-05-21 Lu Chen , Yuxuan Huang , Yixing Li , Dongrui Liu , Qihan Ren , Shuai Zhao , Kun Kuang , Zilong Zheng , Quanshi Zhang

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when…

人工智能 · 计算机科学 2026-04-20 Saloni Dash , Amélie Reymond , Emma S. Spiro , Aylin Caliskan