相关论文: Consistency Training Helps Stop Sycophancy and Jai…

Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promising new alignment paradigm to mitigate such failures by…

As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning…

Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts…

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses…

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt…

Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to…

Modern large language models (LLMs) are increasingly fine-tuned via reinforcement learning from human feedback (RLHF) or related reward optimisation schemes. While such procedures improve perceived helpfulness, we investigate whether…

Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we…

This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive conceptual change. Yet preference-aligned LLMs can trade epistemic rigor for agreeableness.…

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually…

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown particular strength in improving the performance of…

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine…

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and…

Large Language Models (LLMs) are expected to provide helpful and harmless responses, yet they often exhibit sycophancy--conforming to user beliefs regardless of factual accuracy or ethical soundness. Prior research on sycophancy has…

Standard practice within Reinforcement Learning from Human Feedback (RLHF) involves optimizing against a Reward Model (RM), which itself is trained to reflect human preferences for desirable generations. A notable subject that is…

Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…

Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output…