相关论文: IRIS: Implicit Reward-Guided Internal Sifting for …

Generative Vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that, however, are not always grounded in the input image. We investigate this phenomenon, usually referred to as "hallucination" and show…

Aligning large VLMs with human preferences is a challenging task, as methods like RLHF and DPO often overfit to textual information or exacerbate hallucinations. Although augmenting negative image samples partially addresses these pitfalls,…

Continuous sparsification strategies are among the most effective methods for reducing the inference costs and memory demands of large-scale neural networks. A key factor in their success is the implicit $L_1$ regularization induced by…

As Multimodal Large Language Models (MLLMs) gain widespread applicability, it is becoming increasingly desirable to adapt them for diverse user needs. In this paper, we study the adaptation of MLLMs through controlled decoding. To achieve…

The Group Relative Policy Optimization (GRPO) algorithm has demonstrated considerable success in enhancing the reasoning capabilities of large language models (LLMs), as evidenced by DeepSeek-R1. However, the absence of intermediate…

While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical trade-off between capability and reliability. This work…

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation:…

Large vision-language models (LVLMs) have shown promising performance on a variety of vision-language tasks. However, they remain susceptible to hallucinations, generating outputs misaligned with visual content or instructions. While…

We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic…

Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks. Despite this, their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence…

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model…

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

We study a class of reinforcement learning problems where the reward signals for policy learning are generated by an internal reward model that is dependent on and jointly optimized with the policy. This interdependence between the policy…

In an era of countless content offerings, recommender systems alleviate information overload by providing users with personalized content suggestions. Due to the scarcity of explicit user feedback, modern recommender systems typically…

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to design. In many cases, only imperfect rewards are available,…

The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including value alignment and robot learning from demonstration. Despite significant algorithmic contributions in recent years, IRL remains an ill-posed…

The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypotheses. While recent…

AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, such hallucinations are not equally problematic: some hallucination contents could be…

Recommender systems (RecSys) have become critical tools for enhancing user engagement by delivering personalized content across diverse digital platforms. Recent advancements in large language models (LLMs) demonstrate significant potential…