Related papers: Nanbeige4-3B Technical Report: Exploring the Front…

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting starting only from unlabeled seed questions with no ground-truth…

Large language models (LLMs) are considered important approaches towards foundational machine intelligence, achieving remarkable success in Natural Language Processing and multimodal tasks, among others. However, the carbon footprints and…

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

The paradigm shift in large language models (LLMs) from instinctive responses to chain-of-thought (CoT) reasoning has fueled two prevailing assumptions: (1) reasoning capabilities only emerge in sufficiently large models, and (2) such…

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…

While Large Language Models show remarkable performance in natural language understanding, their resource-intensive nature makes them less accessible. In contrast, smaller language models such as MiniCPM offer more sustainable scalability,…

Language models have become increasingly popular in recent years for tasks like information retrieval. As use-cases become oriented toward specific domains, fine-tuning becomes default for standard performance. To fine-tune these models for…

With the increasing size of large language models, layer pruning has gained increased attention as a hardware-friendly approach for model compression. However, existing layer pruning methods struggle to simultaneously address key practical…

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the…

Large Language Models have shown impressive capabilities in coding tasks like code generation and code completion, as they have been trained on a large amount of code data. Also, since one of the core pretraining objectives is Next Token…

Most language models face a fundamental tradeoff where powerful capabilities require substantial computational resources. We shatter this constraint with Jan-nano, a 4B parameter language model that redefines efficiency through radical…

When a language model answers a table question, users have no way to verify which cells informed which reasoning steps. We introduce RSAT, a method that trains small language models (SLMs, 1-8B) to produce step-by-step reasoning with…

Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors…

In recent years, the application of behavioral testing in Natural Language Processing (NLP) model evaluation has experienced a remarkable and substantial growth. However, the existing methods continue to be restricted by the requirements…

The majority of data in businesses and industries is stored in tables, databases, and data warehouses. Reasoning with table-structured data poses significant challenges for large language models (LLMs) due to its hidden semantics, inherent…

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural…

High-quality supervised fine-tuning (SFT) data are crucial for eliciting strong capabilities from pretrained large language models (LLMs). Typically, instructions are paired with multiple responses sampled from other LLMs, which are often…

While pre-training and fine-tuning, e.g., BERT~\citep{devlin2018bert}, GPT-2~\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online…

Although LLMs have demonstrated improved performance by scaling parallel test-time compute, doing so relies on generating reasoning paths that are both diverse and accurate. For challenging problems, the forking tokens that trigger diverse…