Related papers: CLARIFY: Contrastive Preference Reinforcement Lear…

Deep reinforcement learning (DRL) algorithms have achieved great success on sequential decision-making problems, yet is criticized for the lack of data-efficiency and explainability. Especially, explainability of subtasks is critical in…

Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and information retrieval. Collaborative filtering algorithms based on…

Binary choices, as often used for reinforcement learning from human feedback (RLHF), convey only the direction of a preference. A person may choose apples over oranges and bananas over grapes, but which preference is stronger? Strength is…

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable…

Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents…

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

The adoption of Reinforcement Learning (RL) in several human-centred applications provides robots with autonomous decision-making capabilities and adaptability based on the observations of the operating environment. In such scenarios,…

Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction. However, the observed feedback usually suffer…

Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with human intent. However, its effectiveness is often limited by…

Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling…

Large Language Models (LLMs) adapted via contrastive learning excel in general representation learning but struggle in vertical domains like chemistry and law, primarily due to a lack of domain-specific knowledge. This work identifies a…

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt…

Personalized retrieval-augmented generation (RAG) aims to produce user-tailored responses by incorporating retrieved user profiles alongside the input query. Existing methods primarily focus on improving retrieval and rely on large language…

Coping with ambiguous questions has been a perennial problem in real-world dialogue systems. Although clarification by asking questions is a common form of human interaction, it is hard to define appropriate questions to elicit more…

Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium…

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the…

Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier…

Accurately modeling users' evolving preferences from sequential interactions remains a central challenge in recommender systems. Recent studies emphasize the importance of capturing multiple latent intents underlying user behaviors.…

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…