相关论文: AERO: Autonomous Evolutionary Reasoning Optimizati…

Two-stage adaptive robust optimization (ARO) is a powerful approach for planning under uncertainty, balancing first-stage decisions with recourse decisions made after uncertainty is realized. To account for uncertainty, modelers typically…

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…

In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised…

Large audio language models (ALMs) extend LLMs with auditory understanding. A common approach freezes the LLM and trains only an adapter on self-generated targets. However, this fails for reasoning LLMs (RLMs) whose built-in…

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy…

Enhancement reports (ERs) serve as a critical communication channel between users and developers, capturing valuable suggestions for software improvement. However, manually processing these reports is resource-intensive, leading to delays…

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…

Large Reasoning Models (LRMs) often suffer from the ``over-thinking'' problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitigate this issue, such as length penalties or routing…

Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is…

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

We propose an efficient layer-specific optimization (ELO) method designed to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs). This approach addresses the common challenges of high…

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…

Recent advancements in artificial intelligence have propelled the capabilities of Large Language Models, yet their ability to mimic nuanced human reasoning remains limited. This paper introduces a novel conceptual enhancement to LLMs,…

Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-based policy into Internal Layer Policies and Internal…

Large Reasoning Models (LRMs) have achieved impressive performance on complex reasoning tasks by generating detailed chain-of-thought (CoT) explanations. However, these responses are often excessively long, containing redundant reasoning…

The automated generation of layouts is vital for embodied intelligence and autonomous systems, supporting applications from virtual environment construction to home robot deployment. Current approaches, however, suffer from spatial…

Automatic Prompt Optimization (APO) improves large language model (LLM) performance by refining prompts for specific tasks. However, prior APO methods typically focus only on user prompts, rely on unstructured feedback, and require large…

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…