Related papers: Training Language Models to Critique With Multi-ag…

Large language models (LLMs) excel in natural language generation but often confidently produce incorrect responses, especially in tasks like mathematical reasoning. Chain-of-thought prompting, self-verification, and multi-agent debate are…

Aim. There are 10s of thousands of code review comments each week at Meta. We developed Metamate for Code Review (MetaMateCR) that provides AI-assisted fixes for reviewer comments in production at scale. Method. We developed an internal…

Finding an agreement among diverse opinions is a challenging topic in multiagent systems. Recently, large language models (LLMs) have shown great potential in addressing this challenge due to their remarkable capabilities in comprehending…

Reinforcement learning (RL) has emerged as a powerful paradigm for improving large language models beyond supervised fine-tuning, yet sustaining performance gains at scale remains an open challenge, as data diversity and structure, rather…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Machine learning (ML) has significantly advanced text classification by enabling automated understanding and categorization of complex, unstructured textual data. However, accurately capturing nuanced linguistic patterns and contextual…

Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve…

Large Language Models (LLMs) show strong potential for automating model generation from natural-language descriptions. A common approach begins with an initial model generation, followed by an iterative critique-refine loop in which the…

This work investigates whether synthetic emotional chain-of-thought data can improve the emotional reasoning abilities of smaller open large language models (LLMs). We design a multi-agent generation pipeline that produces therapy-style…

Language model heavily depends on high-quality data for optimal performance. Existing approaches rely on manually designed heuristics, the perplexity of existing models, training classifiers, or careful prompt engineering, which require…

The LLM-as-a-judge paradigm enables flexible, user-defined evaluation, but its effectiveness is often limited by the scarcity of diverse, representative data for refining criteria. We present a tool that integrates synthetic data generation…

Systematic literature reviews and meta-analyses are essential for synthesizing research insights, but they remain time-intensive and labor-intensive due to the iterative processes of screening, evaluation, and data extraction. This paper…

While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing factual quotations or fail to provide quotes that exceed…

Extending the capabilities of Large Language Models (LLMs) with functions or tools for environment interaction has led to the emergence of the agent paradigm. In industry, training an LLM is not always feasible because of the scarcity of…

Data visualization generation using Large Language Models (LLMs) has shown promising results but often produces suboptimal visualizations that require human intervention for improvement. In this work, we introduce VIS-Shepherd, a…

Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the…

Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data. While the open development of large high-quality English pre-training datasets has seen substantial recent progress, training…

Large language models (LLMs) are increasingly used to support creative tasks such as research idea generation. While recent work has shown that structured dialogues between LLMs can improve the novelty and feasibility of generated ideas,…

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…

Feature transformation involves generating a new set of features from the original dataset to enhance the data's utility. In certain domains like material performance screening, dimensionality is large and collecting labels is expensive and…