Related papers: A self-evolving multi-role collaborative framework…
We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of single-hop…
Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…
With the rapid advancement of Large Language Models (LLMs), LLM-based approaches have demonstrated strong problem-solving capabilities across various domains. However, in automatic programming, a single LLM is typically limited to…
Autoformalization is the task of automatically translating mathematical content written in natural language to a formal language expression. The growing language interpretation capabilities of Large Language Models (LLMs), including in…
This resource paper addresses the challenge of evaluating Information Retrieval (IR) systems in the era of autoregressive Large Language Models (LLMs). Traditional methods relying on passage-level judgments are no longer effective due to…
Large Language Models (LLMs) exhibit impressive performance across various domains but still struggle with arithmetic reasoning tasks. Recent work shows the effectiveness of prompt design methods in enhancing reasoning capabilities.…
Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on…
Masked generative models (MGMs) have shown impressive generative ability while providing an order of magnitude efficient sampling steps compared to continuous diffusion models. However, MGMs still underperform in image synthesis compared to…
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad…
Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on…
Expensive optimization tasks are ubiquitous in real-world applications, demanding highly specialized solvers. While LLM-driven automated solver generation shows promise, current paradigms face three critical issues when tackling expensive…
Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP techniques. Large Language Models (LLMs) offer the potential…
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a…
Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex…
The automatic generation of high-quality mathematical problems is practically valuable in many educational scenarios. Large multimodal model provides a novel technical approach for the mathematical problem generation because of its wide…
Recent research in retrieval-augmented generation (RAG) has concentrated on retrieving useful information from candidate documents. However, numerous methodologies frequently neglect the calibration capabilities of large language models…
Despite their outstanding capabilities, large language models (LLMs) are prone to hallucination and producing factually incorrect information. This challenge has spurred efforts in attributed text generation, which prompts LLMs to generate…
With an increasing number of parameters and pre-training data, generative large language models (LLMs) have shown remarkable capabilities to solve tasks with minimal or no task-related examples. Notably, LLMs have been successfully employed…
With the rapid development of large language models (LLMs), the applications of LLMs have grown substantially. In the education domain, LLMs demonstrate significant potential, particularly in automatic text generation, which enables the…
Solving tabular math word problems (TMWPs) has become a critical role in evaluating the mathematical reasoning ability of large language models (LLMs), where large-scale TMWP samples are commonly required for LLM fine-tuning. Since the…