Related papers: Language Models Learn to Mislead Humans via RLHF

Large Language Models (LLMs) have demonstrated exceptional performance on a range of downstream NLP tasks by generating text that closely resembles human writing. However, the ease of achieving this similarity raises concerns from potential…

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…

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about…

Recent advancements in natural language processing by large language models (LLMs), such as GPT-4, have been suggested to approach Artificial General Intelligence. And yet, it is still under dispute whether LLMs possess similar reasoning…

There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claims to be iteratively refined over time. This process requires…

In this article, we investigate the alignment of Large Language Models according to human preferences. We discuss the features of training a Preference Model, which simulates human preferences, and the methods and details we found essential…

Large language models exhibit a peculiar epistemic pathology: they speak as if they know, even when they do not. This paper argues that such confident fabrication, what I call the polite liar, is a structural consequence of reinforcement…

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge…

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading 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…

Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounded by the multimodal information in context. To address the…

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Large language models (LLMs) undergo a three-phase training process: unsupervised pre-training, supervised fine-tuning (SFT), and learning from human feedback (RLHF/DPO). Notably, it is during the final phase that these models are exposed…

The demand for regulating potentially risky behaviors of large language models (LLMs) has ignited research on alignment methods. Since LLM alignment heavily relies on reward models for optimization or evaluation, neglecting the quality of…

Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans…

To better align Large Language Models (LLMs) with human judgment, Reinforcement Learning from Human Feedback (RLHF) learns a reward model and then optimizes it using regularized RL. Recently, direct alignment methods were introduced to…

As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human behavior. In this work, using hypothesis testing, we present…

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

Large language models (LLMs) exhibit robust capabilities in text generation and comprehension, mimicking human behavior and exhibiting synthetic personalities. However, some LLMs have displayed offensive personality, propagating toxic…

Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assuming, implicitly or explicitly, a model of human preferences. A preference model that poorly…