Related papers: Structure-Guided Memory Consolidation for Mitigati…
Grammatical error correction (GEC) is a task dedicated to rectifying texts with minimal edits, which can be decoupled into two components: detection and correction. However, previous works have predominantly focused on direct correction,…
While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucial aspect of text chunking within its workflow. This paper…
Retrieval-augmented generation (RAG) improves knowledge-intensive question answering by incorporating external evidence. However, existing RAG methods still suffer from hallucinations and subtle reasoning errors. Recent studies introduce…
Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks…
The increasing volume and complexity of scientific literature demand robust methods for organizing and understanding research documents. In this study, we investigate whether structured knowledge, specifically, subject-predicate-object…
The application of cognitive mechanisms to support knowledge acquisition is, from our point of view, crucial for making the resulting models coherent, efficient, credible, easy to use and understandable. In particular, there are two…
Large Language Models (LLMs) are increasingly embedded in academic writing practices. Although numerous studies have explored how researchers employ these tools for scientific writing, their concrete implementation, limitations, and design…
Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced model, especially…
The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retrieval synthesis stage--where agents must digest massive amounts…
Nowadays, with the booming development of the Internet, people benefit from its convenience due to its open and sharing nature. A large volume of natural language texts is being generated by users in various forms, such as search queries,…
Metrics are the foundation for automatic evaluation in grammatical error correction (GEC), with their evaluation of the metrics (meta-evaluation) relying on their correlation with human judgments. However, conventional meta-evaluations in…
Software bug reports often lack crucial information (e.g., steps to reproduce), which makes bug resolution challenging. Developers thus ask follow-up questions to capture additional information. However, according to existing evidence, bug…
The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and…
This research introduces ScoreRAG, an approach to enhance the quality of automated news generation. Despite advancements in Natural Language Processing and large language models, current news generation methods often struggle with…
The emergence of large language models offers new possibilities for structured exploration of scientific knowledge. Rather than viewing scientific discovery as isolated ideas or content, we propose a structured approach that emphasizes the…
Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…
Automating code review with Large Language Models (LLMs) shows immense promise, yet practical adoption is hampered by their lack of reliability, context-awareness, and control. To address this, we propose Specification-Grounded Code Review…
Systematic reviews require the use of rigorously designed search strategies to ensure both comprehensive retrieval and minimization of bias. Conventional manual approaches, although methodologically systematic, are resource-intensive and…
Clustering aims to group similar objects together while separating dissimilar ones apart. Thereafter, structures hidden in data can be identified to help understand data in an unsupervised manner. Traditional clustering methods such as…
Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is…