Related papers: Compositional Bias Control in Large Language Model…

Large Language Model (LLM)-based recommendation systems excel in delivering comprehensive suggestions by deeply analyzing content and user behavior. However, they often inherit biases from skewed training data, favoring mainstream content…

Large Language Models (LLMs) are increasingly deployed to curate and rank human-created content, yet the nature and structure of their biases in these tasks remains poorly understood: which biases are robust across providers and platforms,…

Large language models(LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences. However, this process can inadvertently lead to these models acquiring biases and stereotypes prevalent in…

Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have…

Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a…

Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we…

Auto-evaluation is crucial for assessing response quality and offering feedback for model development. Recent studies have explored training large language models (LLMs) as generative judges to evaluate and critique other models' outputs.…

Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. While pre-training remains out of reach for most researchers due to the compute required, fine-tuning has…

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue…

Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e.,…

Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine tuning on user data. In this work, we adopt a mechanistic…

While large language models (LLMs) demonstrate strong reasoning capabilities utilizing reinforcement learning (RL) with verifiable reward, whether large vision-language models (VLMs) can directly inherit such capabilities through similar…

Auditing Large Language Models (LLMs) to discover their biases and preferences is an emerging challenge in creating Responsible Artificial Intelligence (AI). While various methods have been proposed to elicit the preferences of such models,…

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalization gap. We take…

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary is due to LLM's bias in evaluating their own output. In this…

Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to…

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language models with the speech…