Related papers: zELO: ELO-inspired Training Method for Rerankers a…

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters),…

Current Large Language Models (LLMs) have shown strong reasoning capabilities in commonsense question answering benchmarks, but the process underlying their success remains largely opaque. As a consequence, recent approaches have equipped…

The effective training of Large Language Models (LLMs) for function calling faces a critical challenge: balancing exploration of complex reasoning paths with stable policy optimization. Standard methods like Supervised Fine-Tuning (SFT)…

There has been recent interest in improving performance of simple models for multiple reasons such as interpretability, robust learning from small data, deployment in memory constrained settings as well as environmental considerations. In…

Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-RL methods require partially or fully on-policy data, i.e.,…

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Large language models (LLMs) have significantly advanced natural language processing, excelling in areas like text generation, summarization, and question-answering. Despite their capabilities, these models face challenges when fine-tuned…

Traditional text classification approaches often require a good amount of labeled data, which is difficult to obtain, especially in restricted domains or less widespread languages. This lack of labeled data has led to the rise of…

Reinforcement learning is now widely adopted as the final stage of large language model training, especially for reasoning-style tasks such as maths problems. Typically, models attempt each question many times during a single training step…

A significant shortcoming of current state-of-the-art (SOTA) named-entity recognition (NER) systems is their lack of generalization to unseen domains, which poses a major problem since obtaining labeled data for NER in a new domain is…

The recent explosive interest in the reasoning capabilities of large language models, such as DeepSeek-R1, has demonstrated remarkable success through reinforcement learning-based fine-tuning frameworks, exemplified by methods like Group…

Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a significant and promising direction, there still exists many…

In reinforcement learning (RL) research, simulations enable benchmarks between algorithms, as well as prototyping and hyper-parameter tuning of agents. In order to promote RL both in research and real-world applications, frameworks are…

What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) show such broad visual reasoning is within reach, but the recipe behind…

Zeroth-order (ZO) optimization has long been favored for its biological plausibility and its capacity to handle non-differentiable objectives, yet its computational complexity has historically limited its application in deep neural…

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…

Effective decision making involves flexibly relating past experiences and relevant contextual information to a novel situation. In deep reinforcement learning (RL), the dominant paradigm is for an agent to amortise information that helps…

We develop a method for training small-scale (under 100M parameter) neural information retrieval models with as few as 10 gold relevance labels. The method depends on generating synthetic queries for documents using a language model (LM),…