相关论文: RBCorr: Response Bias Correction in Language Model…

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

Steering methods for language models (LMs) seek to provide fine-grained and interpretable control over model generations by variously changing model inputs, weights, or representations to adjust behavior. Recent work has shown that…

Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…

In this project, we want to explore the newly emerging field of prompt engineering and apply it to the downstream task of detecting LM biases. More concretely, we explore how to design prompts that can indicate 4 different types of biases:…

Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep…

Do generative AI models, particularly large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can these biases be mitigated? Drawing on the cognitive psychology and experimental…

Pre-trained language models (LLMs) such as GPT-3 can carry fluent, multi-turn conversations out-of-the-box, making them attractive materials for chatbot design. Further, designers can improve LLM chatbot utterances by prepending textual…

The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning…

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their predictions are influenced by the order of answer choices, which would indicate a form of position…

Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases…

Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data. Previous work addresses this issue by employing approximate Bayesian estimation…

Recent Large Reasoning Models (LRMs) with thinking traces have shown strong performance on English reasoning tasks. However, their ability to think in other languages is less studied. This capability is as important as answer accuracy for…

Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods. Nevertheless, while LoRA improves efficiency,…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

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…

Large Language Models (LLMs) have demonstrated impressive mathematical reasoning capabilities, yet their performance remains brittle to minor variations in problem description and prompting strategy. Furthermore, reasoning is vulnerable to…

Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further…

Reinforcement Learning with Human Feedback (RLHF) has emerged as a key paradigm for task-specific fine-tuning of language models using human preference data. While numerous publicly available preference datasets provide pairwise comparisons…