Related papers: Power Distribution Bridges Sampling, Self-Reward R…

Large Language Models (LLMs) have achieved impressive results across numerous NLP tasks but still encounter difficulties in machine translation. Traditional methods to improve translation have typically involved fine-tuning LLMs using…

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

While deep reinforcement learning has achieved promising results in challenging decision-making tasks, the main bones of its success --- deep neural networks are mostly black-boxes. A feasible way to gain insight into a black-box model is…

Despite substantial progress in multilingual extractive Question Answering (QA), models with high and uniformly distributed performance across languages remain challenging, especially for languages with limited resources. We study…

Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with…

Large language models (LLMs) have garnered increasing attention owing to their powerful logical reasoning capabilities. Generally, larger LLMs (L-LLMs) that require paid interfaces exhibit significantly superior performance compared to…

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We study this question in a controlled zero-shot, one-hop,…

Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are estimated without ground-truth supervision. Most existing…

Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data,…

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide response selection…

Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel…

In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…

The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination (generating false information) and the high cost of proprietary models. To address these challenges, we propose a retrieval-augmented…

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

Distilling robust reasoning capabilities from large language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent advances, distilled models frequently suffer from superficial…

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

Improving performance on complex tasks and enabling interpretable decision making in large language models (LLMs), especially for clinical applications, requires effective reasoning. Yet this remains challenging without supervised…

The detection of mental health problems from social media and the interpretation of these results have been extensively explored. Research has shown that incorporating clinical symptom information into a model enhances domain expertise,…