no code implementations • 4 Feb 2025 • Qianhao Yuan, Yanjiang Liu, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun
To investigate whether attention among visual tokens is necessary, we propose a new self-attention mechanism, NAAViT (\textbf{N}o \textbf{A}ttention \textbf{A}mong \textbf{Vi}sual \textbf{T}okens), which eliminates this type of attention.
1 code implementation • 7 Jan 2025 • Hao Zheng, Xinyan Guan, Hao Kong, Jia Zheng, Hongyu Lin, Yaojie Lu, Ben He, Xianpei Han, Le Sun
Automatically generating presentations from documents is a challenging task that requires balancing content quality, visual design, and structural coherence.
no code implementations • 3 Jan 2025 • Yanjiang Liu, Shuhen Zhou, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Hongyu Lin, Ben He, Xianpei Han, Le Sun
Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs).
1 code implementation • 18 Nov 2024 • Xinyan Guan, Yanjiang Liu, Xinyu Lu, Boxi Cao, Ben He, Xianpei Han, Le Sun, Jie Lou, Bowen Yu, Yaojie Lu, Hongyu Lin
The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals.
no code implementations • 5 Nov 2024 • Ying Zhou, Xinyao Wang, Yulei Niu, Yaojie Shen, Lexin Tang, Fan Chen, Ben He, Le Sun, Longyin Wen
Recent advancements in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis.
no code implementations • 8 Oct 2024 • Xueru Wen, Jie Lou, Yaojie Lu, Hongyu Lin, Xing Yu, Xinyu Lu, Ben He, Xianpei Han, Debing Zhang, Le Sun
Reward Models (RMs) are crucial for aligning language models with human preferences.
no code implementations • 23 Aug 2024 • Ruiyang Xu, Jialun Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Ben He, Shing-Chi Cheung, Le Sun
However, there is an unignorable programming language bias in existing code benchmarks -- over 95% code generation benchmarks are dominated by Python, leaving the LLMs' capabilities in other programming languages such as Java and C/C++ unknown.
no code implementations • 18 Jun 2024 • Xueru Wen, Xinyu Lu, Xinyan Guan, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun
Previous learning-based methods focus on detecting knowledge boundaries and finetuning models with instance-level feedback, but they suffer from inaccurate signals due to off-policy data sampling and coarse-grained feedback.
2 code implementations • 13 Jun 2024 • Ying Zhou, Ben He, Le Sun
Furthermore, through adversarial learning experiments, we investigate the impact of perturbation data augmentation on the robustness of AI-text detectors.
1 code implementation • 3 Jun 2024 • Boxi Cao, Keming Lu, Xinyu Lu, Jiawei Chen, Mengjie Ren, Hao Xiang, Peilin Liu, Yaojie Lu, Ben He, Xianpei Han, Le Sun, Hongyu Lin, Bowen Yu
Alignment is the most critical step in building large language models (LLMs) that meet human needs.
1 code implementation • 16 Apr 2024 • Xiaoyang Chen, Ben He, Hongyu Lin, Xianpei Han, Tianshu Wang, Boxi Cao, Le Sun, Yingfei Sun
The practice of Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with retrieval systems, has become increasingly prevalent.
1 code implementation • 2 Apr 2024 • Ying Zhou, Ben He, Le Sun
While well-trained text detectors have demonstrated promising performance on unseen test data, recent research suggests that these detectors have vulnerabilities when dealing with adversarial attacks such as paraphrasing.
2 code implementations • 23 Feb 2024 • Qiaoyu Tang, Jiawei Chen, Zhuoqun Li, Bowen Yu, Yaojie Lu, Cheng Fu, Haiyang Yu, Hongyu Lin, Fei Huang, Ben He, Xianpei Han, Le Sun, Yongbin Li
However, current interactions between IR systems and LLMs remain limited, with LLMs merely serving as part of components within IR systems, and IR systems being constructed independently of LLMs.
no code implementations • 22 Feb 2024 • Ning Bian, Xianpei Han, Hongyu Lin, Yaojie Lu, Ben He, Le Sun
Building machines with commonsense has been a longstanding challenge in NLP due to the reporting bias of commonsense rules and the exposure bias of rule-based commonsense reasoning.
1 code implementation • 1 Feb 2024 • Xinlin Peng, Ying Zhou, Ben He, Le Sun, Yingfei Sun
This paper aims to bridge this gap by constructing AIG-ASAP, an AI-generated student essay dataset, employing a range of text perturbation methods that are expected to generate high-quality essays while evading detection.
no code implementations • 22 Nov 2023 • Xinyan Guan, Yanjiang Liu, Hongyu Lin, Yaojie Lu, Ben He, Xianpei Han, Le Sun
Incorporating factual knowledge in knowledge graph is regarded as a promising approach for mitigating the hallucination of large language models (LLMs).
1 code implementation • 20 Aug 2023 • Xueru Wen, Xiaoyang Chen, Xuanang Chen, Ben He, Le Sun
Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process.
no code implementations • 31 Jul 2023 • Xuanang Chen, Ben He, Le Sun, Yingfei Sun
Neural ranking models (NRMs) have undergone significant development and have become integral components of information retrieval (IR) systems.
no code implementations • 8 May 2023 • Ning Bian, Hongyu Lin, Peilin Liu, Yaojie Lu, Chunkang Zhang, Ben He, Xianpei Han, Le Sun
LLMs, as AI agents, can observe external information, which shapes their cognition and behaviors.
1 code implementation • 3 May 2023 • Xiaoyang Chen, Yanjiang Liu, Ben He, Le Sun, Yingfei Sun
The Differentiable Search Index (DSI) is a novel information retrieval (IR) framework that utilizes a differentiable function to generate a sorted list of document identifiers in response to a given query.
no code implementations • 3 May 2023 • Xuanang Chen, Ben He, Zheng Ye, Le Sun, Yingfei Sun
Additionally, current methods rely heavily on the use of a well-imitated surrogate NRM to guarantee the attack effect, which makes them difficult to use in practice.
no code implementations • 29 Mar 2023 • Ning Bian, Xianpei Han, Le Sun, Hongyu Lin, Yaojie Lu, Ben He, Shanshan Jiang, Bin Dong
(4) Can ChatGPT effectively leverage commonsense for answering questions?
no code implementations • 9 May 2022 • Ying Zhou, Xuanang Chen, Ben He, Zheng Ye, Le Sun
Knowledge graph completion (KGC) aims to infer missing knowledge triples based on known facts in a knowledge graph.
1 code implementation • 25 Apr 2022 • Xiaoyang Chen, Ben He, Le Sun
While large-scale pre-trained language models like BERT have advanced the state-of-the-art in IR, its application in query performance prediction (QPP) is so far based on pointwise modeling of individual queries.
no code implementations • 19 Jul 2021 • Ning Bian, Xianpei Han, Bo Chen, Hongyu Lin, Ben He, Le Sun
In this paper, we propose a new framework for unsupervised MRC.
no code implementations • 17 Apr 2021 • Xiaoyang Chen, Kai Hui, Ben He, Xianpei Han, Le Sun, Zheng Ye
BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Lingyong Yan, Xianpei Han, Ben He, Le Sun
Bootstrapping for entity set expansion (ESE) has been studied for a long period, which expands new entities using only a few seed entities as supervision.
4 code implementations • 16 Sep 2020 • Xuanang Chen, Ben He, Kai Hui, Le Sun, Yingfei Sun
Despite the effectiveness of utilizing the BERT model for document ranking, the high computational cost of such approaches limits their uses.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Zhi Zheng, Kai Hui, Ben He, Xianpei Han, Le Sun, Andrew Yates
Query expansion aims to mitigate the mismatch between the language used in a query and in a document.
1 code implementation • 20 Aug 2020 • Canjia Li, Andrew Yates, Sean MacAvaney, Ben He, Yingfei Sun
In this work, we explore strategies for aggregating relevance signals from a document's passages into a final ranking score.
Ranked #2 on
Ad-Hoc Information Retrieval
on TREC Robust04
no code implementations • IJCNLP 2019 • Lingyong Yan, Xianpei Han, Le Sun, Ben He
Bootstrapping for Entity Set Expansion (ESE) aims at iteratively acquiring new instances of a specific target category.
no code implementations • 20 May 2019 • Yiyu Wang, Jungang Xu, Yingfei Sun, Ben He
Image captioning is a challenging task and attracting more and more attention in the field of Artificial Intelligence, and which can be applied to efficient image retrieval, intelligent blind guidance and human-computer interaction, etc.
1 code implementation • EMNLP 2018 • Canjia Li, Yingfei Sun, Ben He, Le Wang, Kai Hui, Andrew Yates, Le Sun, Jungang Xu
Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document vocabulary mismatches.
Ranked #9 on
Ad-Hoc Information Retrieval
on TREC Robust04
no code implementations • ACL 2018 • Cancan Jin, Ben He, Kai Hui, Le Sun
Existing automated essay scoring (AES) models rely on rated essays for the target prompt as training data.