相关论文: Preference Learning with Lie Detectors can Induce …

Quality of datasets plays an important role in large language model (LLM) alignment. In collecting human feedback, however, preference flipping is ubiquitous and causes corruption in data annotation; the issue necessitates the alignment…

Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple…

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference…

Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large language and…

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing…

Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In…

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced…

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as…

Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. In the past it uses reinforcement learning from human feedback…

Automated verbal deception detection using methods from Artificial Intelligence (AI) has been shown to outperform humans in disentangling lies from truths. Research suggests that transparency and interpretability of computational methods…

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

Computational preference elicitation methods are tools used to learn people's preferences quantitatively in a given context. Recent works on preference elicitation advocate for active learning as an efficient method to iteratively construct…

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

The application of Reinforcement Learning (RL) in real world environments can be expensive or risky due to sub-optimal policies during training. In Offline RL, this problem is avoided since interactions with an environment are prohibited.…

Preference learning methods such as Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy and length bias in today's language models and potentially severe goal misgeneralization…

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

It is difficult for humans to distinguish the true and false of rumors, but current deep learning models can surpass humans and achieve excellent accuracy on many rumor datasets. In this paper, we investigate whether deep learning models…

The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences.…

While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this question using a novel dataset of realistic moral…