Related papers: Language Models Learn to Mislead Humans via RLHF

Recent studies show that instruction tuning (IT) and reinforcement learning from human feedback (RLHF) improve the abilities of large language models (LMs) dramatically. While these tuning methods can help align models with human objectives…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

As natural language becomes the default interface for human-AI interaction, there is a need for LMs to appropriately communicate uncertainties in downstream applications. In this work, we investigate how LMs incorporate confidence in…

Despite notable advancements in Multimodal Large Language Models (MLLMs), most state-of-the-art models have not undergone thorough alignment with human preferences. This gap exists because current alignment research has primarily achieved…

Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with…

Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be…

Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research…

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…

Large Language Models (LLMs) have shown remarkable success on a wide range of math and reasoning benchmarks. However, we observe that they often struggle when faced with unreasonable math problems. Instead of recognizing these issues,…

Modeling complex subjective tasks in Natural Language Processing, such as recognizing emotion and morality, is considerably challenging due to significant variation in human annotations. This variation often reflects reasonable differences…

Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output diversity. This trade-off between diversity and alignment…

Autoregressive Large Language Models (LLMs) trained for next-word prediction have demonstrated remarkable proficiency at producing coherent text. But are they equally adept at forming coherent probability judgments? We use probabilistic…

Large Language Models (LLMs) often exhibit sycophancy, distorting responses to align with user beliefs, notably by readily agreeing with user counterarguments. Paradoxically, LLMs are increasingly adopted as successful evaluative agents for…

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…

Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding. However, existing studies have concentrated mainly on visual-textual…

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where…

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference…

Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness critical. A significant and underexplored risk is intentional deception, where an LLM deliberately fabricates…