Related papers: NPO: Learning Alignment and Meta-Alignment through…
Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…
In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training. This misalignment limits the efficiency of Supervised…
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…
Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design.…
The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these advancements, recent methods still rely heavily on substantial paired (labeled) feedback data,…
Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss used in decoupled PPO improves coupled-loss style of algorithms' (e.g.,…
Personalization and contextual coherence are two essential components in building effective persona-grounded dialogue systems. These aspects play a crucial role in enhancing user engagement and ensuring responses are more relevant and…
Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream…
Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function…
Emerging research in Pluralistic Artificial Intelligence (AI) alignment seeks to address how intelligent systems can be designed and deployed in accordance with diverse human needs and values. We contribute to this pursuit with a dynamic…
In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continual learning where…
Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…
While error backpropagation (BP) has dominated the training of nearly all modern neural networks for a long time, it suffers from several biological plausibility issues such as the symmetric weight requirement and synchronous updates.…
Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…
Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…
Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…
Formal verification provides assurances that a probabilistic system satisfies its specification--conditioned on the system model being aligned with reality. We propose alignment monitoring to watch that this assumption is justified. We…
This paper represents a novel online self-learning disturbance observer (SLDO) by benefiting from the combination of a type-2 neuro-fuzzy structure (T2NFS), feedback-error learning scheme and sliding mode control (SMC) theory. The SLDO is…
Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…
In recent years, text-to-speech (TTS) has seen impressive advancements through large-scale language models, achieving human-level speech quality. Integrating human feedback has proven effective for enhancing robustness in these systems.…