Related papers: ADAPT: Actively Discovering and Adapting to Prefer…

Recent advancements in Recommender Systems (RS) have incorporated Reinforcement Learning (RL), framing the recommendation as a Markov Decision Process (MDP). However, offline RL policies trained on static user data are vulnerable to…

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

As large language models (LLMs) demonstrate increasingly advanced capabilities, aligning their behaviors with human values and preferences becomes crucial for their wide adoption. While previous research focuses on general alignment to…

One emergent ability of large language models (LLMs) is that query-specific examples can be included in the prompt at inference time. In this work, we use active learning for adaptive prompt design and call it Active In-context Prompt…

Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their effective deployment…

Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to overcome this challenge using weight updates that do not…

Evaluating LLM agent trajectories is fundamentally task-specific: a code-debugging agent should be judged on Correctness and Error Handling, not on Fluency or Safety. Yet the dominant paradigm -- LLM-as-Judge with a fixed rubric -- applies…

In sequential recommendation, models recommend items based on user's interaction history. To this end, current models usually incorporate information such as item descriptions and user intent or preferences. User preferences are usually not…

Fine-grained control over large language models (LLMs) remains a significant challenge, hindering their adaptability to diverse user needs. While Reinforcement Learning from Human Feedback (RLHF) shows promise in aligning LLMs, its reliance…

Direct Preference Optimization (DPO) has become a standard recipe for aligning large language models, yet it is still unclear what kind of change it actually induces inside the network. This paper argues that DPO does not rewrite a models…

While recent advancements in aligning Large Language Models (LLMs) with recommendation tasks have shown great potential and promising performance overall, these aligned recommendation LLMs still face challenges in complex scenarios. This is…

We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By computing activation-difference vectors for both test prompts and preference pairs and…

In this paper, we introduce a novel learning paradigm for Adaptive Large Language Model (LLM) agents that eliminates the need for fine-tuning the underlying LLMs. Existing approaches are often either rigid, relying on static, handcrafted…

The advent of large language models (LLMs) has spurred considerable interest in advancing autonomous LLMs-based agents, particularly in intriguing applications within smartphone graphical user interfaces (GUIs). When presented with a task…

Many applications of large language models (LLMs), ranging from chatbots to creative writing, require nuanced subjective judgments that can differ significantly across different groups. Existing alignment algorithms can be expensive to…

Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intentions and values, improving context-faithfulness through…

In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, where the complexity of instructions are rapidly increasing.…

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency. Although the application of…