8 papers
Coding Agents are Effective Long-Context Processors
Weili Cao, Xunjian Yin, Bhuwan Dhingra +1
Large Language Models (LLMs) have demonstrated remarkable progress in scaling to access massive contexts. However, the access is via the latent and uninterpretable attention mechan…
Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction
Yilin Li, Xunjian Yin, Yilin Chen +1
Grammatical error correction is a significant task in NLP. Traditional methods based on encoder-decoder models have achieved certain success, but the application of LLMs in this fi…
AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection
Jiatao Li, Mao Ye, Cheng Peng +2
Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot eff…
DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models
Jinxiang Xie, Yilin Li, Xunjian Yin +1
Evaluating the performance of Grammatical Error Correction (GEC) models has become increasingly challenging, as large language model (LLM)-based GEC systems often produce correctio…
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
Yuxi Xie, Anirudh Goyal, Xiaobao Wu +5
Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. However, existing approaches typically im…
Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
Sitao Cheng, Liangming Pan, Xunjian Yin +2
Large language models (LLMs) encode vast amounts of knowledge during pre-training (parametric knowledge, or PK) and can further be enhanced by incorporating contextual knowledge (C…