Related papers: Demonstration Selection for In-Context Learning vi…

While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have…

Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015.…

In-Context Learning (ICL) is a technique by which language models make predictions based on examples provided in their input context. Previously, their context window size imposed a limit on the number of examples that can be shown, making…

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Large Language Models (LLMs) with in-context learning (ICL) ability can quickly adapt to a specific context given a few demonstrations (demos). Recently, Multimodal Large Language Models (MLLMs) built upon LLMs have also shown multimodal…

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general…

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Differential evolution (DE) algorithm is recognized as one of the most effective evolutionary algorithms, demonstrating remarkable efficacy in black-box optimization due to its derivative-free nature. Numerous enhancements to the…

Relational Reinforcement Learning (RRL) can offers various desirable features. Most importantly, it allows for incorporating expert knowledge into the learning, and hence leading to much faster learning and better generalization compared to…

High-quality relevance judgements over large query sets are essential for evaluating Information Retrieval (IR) systems, yet manual annotation remains costly and time-consuming. Large Language Models (LLMs) have recently shown promise as…

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…

Rehearsal-based techniques are commonly used to mitigate catastrophic forgetting (CF) in Incremental learning (IL). The quality of the exemplars selected is important for this purpose and most methods do not ensure the appropriate diversity…

Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Leveraging Multimodal Large Language Models (MLLMs) has become pivotal for advancing Universal Multimodal Embeddings (UME) in addressing diverse cross-modal tasks. Recent studies demonstrate that incorporating generative Chain-of-Thought…

This thesis rigorously studies fundamental reinforcement learning (RL) methods in modern practical considerations, including robust RL, distributional RL, and offline RL with neural function approximation. The thesis first prepares the…

Large language models (LLMs) demonstrate robust capabilities across diverse research domains. However, their performance in universal information extraction (UIE) remains insufficient, especially when tackling structured output scenarios…

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations…