相关论文: Align on the Fly: Adapting Chatbot Behavior to Est…

Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the…

Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end…

Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known as language confusion. Prior mitigation approaches based on…

Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a widely observed phenomenon known as overoptimization, where the…

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve…

This work introduces LAB (Large-scale Alignment for chatBots), a novel methodology designed to overcome the scalability challenges in the instruction-tuning phase of large language model (LLM) training. Leveraging a taxonomy-guided…

Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrationality in human preferences. Recent advancements suggest…

Optimization is ubiquitous. While derivative-based algorithms have been powerful tools for various problems, the absence of gradient imposes challenges on many real-world applications. In this work, we propose Optimization by PROmpting…

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text. We argue that text offers greater expressiveness, enabling users to provide richer feedback than simple…

Large Language Models (LLMs) often memorize sensitive, private, or copyrighted data during pre-training. LLM unlearning aims to eliminate the influence of undesirable data from the pre-trained model while preserving the model's utilities on…

Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering updates but often…

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online…

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes…

RL-based post-training of language models is almost exclusively done using on-policy methods such as PPO. These methods cannot learn from arbitrary sequences such as those produced earlier in training, in earlier runs, by human experts or…

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…