Related papers: A Scientific Reasoning Model for Organic Synthesis…

Large language models (LLMs) have demonstrated strong reasoning abilities across specialized domains, motivating research into their application to legal reasoning. However, existing legal benchmarks often conflate factual recall with…

Large language models (LLMs) perform strongly on many language tasks but still struggle with complex multi-step reasoning across disciplines. Existing reasoning datasets often lack disciplinary breadth, reasoning depth, and diversity, as…

Modern computer-assisted synthesis planning (CASP) systems show promises at generating chemically valid reaction steps but struggle to incorporate strategic considerations such as convergent assembly, protecting group minimization, and…

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

Variant and gene interpretation are fundamental to personalized medicine and translational biomedicine. However, traditional approaches are manual and labor-intensive. Generative language models (LMs) can facilitate this process,…

Retrieval-Augmented Generation (RAG) grounds large language models (LLMs) in external evidence, but fails when retrieved sources conflict or contain outdated or subjective information. Prior work address these issues independently but lack…

Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the…

Retrosynthesis prediction aims to infer the reactant molecule based on a given product molecule, which is a fundamental task in chemical synthesis. However, existing models rely on static pattern-matching paradigm, which limits their…

Chemical reasoning usually involves complex, multi-step processes that demand precise calculations, where even minor errors can lead to cascading failures. Furthermore, large language models (LLMs) encounter difficulties handling…

Quantitative chemistry is central to modern chemical research, yet the ability of large language models (LLMs) to perform its rigorous, step-by-step calculations remains underexplored. To fill this blank, we propose QCBench, a Quantitative…

Reasoning is essential for closed-domain QA systems in which procedural correctness and policy compliance are critical. While large language models (LLMs) have shown strong performance on many reasoning tasks, recent work reveals that their…

While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-answering tasks. This paradigm often results in "black-box"…

The chemical reaction recommendation is to select proper reaction condition parameters for chemical reactions, which is pivotal to accelerating chemical science. With the rapid development of large language models (LLMs), there is growing…

In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond…

Reinforcement learning (RL) is emerging as a powerful paradigm for enabling large language models (LLMs) to perform complex reasoning tasks. Recent advances indicate that integrating RL with retrieval-augmented generation (RAG) allows LLMs…

Since the launch of ChatGPT at the end of 2022, generative dialogue models represented by ChatGPT have quickly become essential tools in daily life. As user expectations increase, enhancing the capability of generative dialogue models to…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conventiona RAG systems under-perform on structured tabular data, largely due to coarse…

The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive…

In knowledge-intensive tasks, especially in high-stakes domains like medicine and law, it is critical not only to retrieve relevant information but also to provide causal reasoning and explainability. Large language models (LLMs) have…

Question Answering (QA) systems face challenges in handling complex questions that require multi-domain knowledge synthesis. The naive RAG models, although effective in information retrieval, struggle with complex questions that require…