相关论文: Decoding-Time Debiasing via Process Reward Models:…

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Large language models (LLMs) increasingly mediate human communication, decision support, content creation, and information retrieval. Despite impressive fluency, these systems frequently produce biased or stereotypical content, especially…

Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinations, stereotypes,…

Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens these cues directly by penalizing or controlling specific…

Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances,…

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.…

Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing debiasing methods…

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for…

Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…

In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model editing methods, which focus on modifying LLMs in a post-hoc…

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

As deep learning models become tasked with more and more decisions that impact human lives, such as criminal recidivism, loan repayment, and face recognition for law enforcement, bias is becoming a growing concern. Debiasing algorithms are…

Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studies explore advanced prompting schemes and post-training…