相关论文: Some things are more CRINGE than others: Iterative…

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the…

Preference learning, or the task of aligning generative models to preference comparison data, has yet to reach the conceptual maturity of classification, density estimation, etc. To close this gap, this work presents a framework to…

Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to select worth-annotating response pairs for cost-efficient annotation while achieving…

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…

Direct Preference Optimization (DPO) has become a popular approach for aligning language models using pairwise preferences. However, in practical post-training pipelines, on-policy generation typically yields multiple candidate responses…

Iterative data generation and model retraining are widely used to align large language models (LLMs). It typically involves a policy model to generate on-policy responses and a reward model to guide training data selection. Direct…

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…

After pre-training, large language models are aligned with human preferences based on pairwise comparisons. State-of-the-art alignment methods (such as PPO-based RLHF and DPO) are built on the assumption of aligning with a single preference…

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences…

The development of largely human-annotated benchmarks has driven the success of deep neural networks in various NLP tasks. To enhance the effectiveness of existing benchmarks, collecting new additional input-output pairs is often too costly…

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained…

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Reward models are pivotal for aligning Large Language Models (LLMs) with human preferences. Existing approaches face two key limitations: Discriminative reward models require large-scale annotated data, as they cannot exploit the preference…

Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely…

Learning from preference-based feedback has recently gained traction as a promising approach to align language models with human interests. While these aligned generative models have demonstrated impressive capabilities across various…

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first…