Related papers: Angles Don't Lie: Unlocking Training-Efficient RL …

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Reinforcement learning (RL) is gaining attention by more and more researchers in quantitative finance as the agent-environment interaction framework is aligned with decision making process in many business problems. Most of the current…

We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in…

State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…

Training loss and throughput can hide distinct internal representation in language-model training. To examine these hidden mechanics, we use spectral measurements as practical and operational diagnostics. Using a controlled family of…

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such…

Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer…

Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train…

Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy.…

Continual learning (CL), which requires the model to learn multiple tasks sequentially, is crucial for large language models (LLMs). Recently, low-rank adaptation~(LoRA), one of the most representative parameter-efficient fine-tuning (PEFT)…

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction…