Related papers: Decoding-Time Debiasing via Process Reward Models:…

Large language models (LLMs) often exhibit strong biases, e.g, against women or in favor of the number 7. We investigate whether LLMs would be able to output less biased answers when allowed to observe their prior answers to the same…

Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at…

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous studies use…

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method…

Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive information is semantically entangled with the task…

Aligning language models with human preferences is crucial for reducing errors and biases in these models. Alignment techniques, such as reinforcement learning from human feedback (RLHF), are typically cast as optimizing a tradeoff between…

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework…

Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this paper, we introduce…

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and…

Employing Large Language Models (LLMs) to assess the quality of generated responses, such as prompting instruct-tuned models or fine-tuning judge models, has become a widely adopted evaluation method. It is also known that such evaluators…

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…

Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By…

Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks.…

Biases in culture, gender, ethnicity, etc. have existed for decades and have affected many areas of human social interaction. These biases have been shown to impact machine learning (ML) models, and for natural language processing (NLP),…

As Vision Language Models (VLMs) gain widespread use, their fairness remains under-explored. In this paper, we analyze demographic biases across five models and six datasets. We find that portrait datasets like UTKFace and CelebA are the…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

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…

Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonly recognized as low-quality, containing inductive biases…

Large Language Models (LLMs) have achieved remarkable success on question answering (QA) tasks, yet they often encode harmful biases that compromise fairness and trustworthiness. Most existing bias mitigation approaches are restricted to…

Several prior works have shown that language models (LMs) can generate text containing harmful social biases and stereotypes. While decoding algorithms play a central role in determining properties of LM generated text, their impact on the…