15 citations · 19 across the 17 of their papers we have counts for
19 papers
SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs
Zhenliang Zhang, Xinyu Hu, Xiaojun Wan
Large language models sometimes inadvertently reproduce passages that are copyrighted, exposing downstream applications to legal risk. Most existing studies for inference-time defe…
Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models
Zhenliang Zhang, Junzhe Zhang, Xinyu Hu +2
Large language models (LLMs) have achieved remarkable success in various tasks, yet they remain vulnerable to faithfulness hallucinations, where the output does not align with the…
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
Zhenliang Zhang, Xinyu Hu, Huixuan Zhang +2
Large language models (LLMs) excel at various natural language processing tasks, but their tendency to generate hallucinations undermines their reliability. Existing hallucination…
LEDOM: Reverse Language Model
Xunjian Yin, Sitao Cheng, Yuxi Xie +6
Autoregressive language models are trained exclusively left-to-right. We explore the complementary factorization, training right-to-left at scale, and ask what reasoning patterns e…
MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text
Junzhe Zhang, Huixuan Zhang, Xinyu Hu +4
Evaluation is important for multimodal generation tasks, while traditional multimodal evaluation metrics suffer from several limitations. With the rapid progress of MLLMs, there is…
NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs
Li Lin, Xinyu Hu, Xiaojun Wan
Large language models (LLMs) achieve impressive performance across domains but face significant challenges when deployed on consumer-grade GPUs or personal devices such as laptops,…
CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing
Zhenghan Yu, Xinyu Hu, Xiaojun Wan
Humor plays a significant role in daily language communication. With the rapid development of large language models (LLMs), natural language processing has made significant strides…
Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators
Jiayi Chang, Mingqi Gao, Xinyu Hu +1
Previous research has shown that LLMs have potential in multilingual NLG evaluation tasks. However, existing research has not fully explored the differences in the evaluation capab…
Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review
Jiatao Li, Yanheng Li, Xinyu Hu +2
We propose an aspect-guided, multi-level perturbation framework to evaluate the robustness of Large Language Models (LLMs) in automated peer review. Our framework explores perturba…
Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
Mingqi Gao, Yixin Liu, Xinyu Hu +3
Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. Due to the high cost and time-consumi…
A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability
Xinyu Hu, Mingqi Gao, Li Lin +2
In NLG meta-evaluation, evaluation metrics are typically assessed based on their consistency with humans. However, we identify some limitations in traditional NLG meta-evaluation a…
Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation
Mingqi Gao, Xinyu Hu, Li Lin +1
The correlation between NLG automatic evaluation metrics and human evaluation is often regarded as a critical criterion for assessing the capability of an evaluation metric. Howeve…
Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
Jiatao Li, Xinyu Hu, Xunjian Yin +1
The integration of documents generated by LLMs themselves (Self-Docs) alongside retrieved documents has emerged as a promising strategy for retrieval-augmented generation systems.…
SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval
Jiatao Li, Xinyu Hu, Xiaojun Wan
Retrieval-Augmented Generation (RAG) has greatly improved large language models (LLMs) by enabling them to generate accurate, contextually grounded responses through the integratio…
Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability
Xinyu Hu, Li Lin, Mingqi Gao +2
The evaluation of natural language generation (NLG) tasks is a significant and longstanding research area. With the recent emergence of powerful large language models (LLMs), some…
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
Junzhe Zhang, Huixuan Zhang, Xunjian Yin +4
Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of…
Are LLM-based Evaluators Confusing NLG Quality Criteria?
Xinyu Hu, Mingqi Gao, Sen Hu +4
Some prior work has shown that LLMs perform well in NLG evaluation for different tasks. However, we discover that LLMs seem to confuse different evaluation criteria, which reduces…
LLM-based NLG Evaluation: Current Status and Challenges
Mingqi Gao, Xinyu Hu, Jie Ruan +2
Evaluating natural language generation (NLG) is a vital but challenging problem in natural language processing. Traditional evaluation metrics mainly capturing content (e.g. n-gram…
Error-Robust Retrieval for Chinese Spelling Check
Xunjian Yin, Xinyu Hu, Jin Jiang +1
Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts, which has a wide range of applications. However, it is confronted with the challenges of i…