Search Results for author: Ben He

Found 35 papers, 16 papers with code

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency

no code implementations4 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.

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

1 code implementation7 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.

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

no code implementations3 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).

Red Teaming

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering

1 code implementation18 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.

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models

no code implementations5 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.

Prompt Engineering Synthetic Data Generation

CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution

no code implementations23 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.

Code Generation HumanEval

On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation

no code implementations18 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.

Hallucination Response Generation

Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors

2 code implementations13 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.

Data Augmentation Text Detection

Towards Scalable Automated Alignment of LLMs: A Survey

1 code implementation3 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.

Survey

Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering

1 code implementation16 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.

Information Retrieval Language Modeling +4

Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack

1 code implementation2 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.

Adversarial Attack Text Detection

Self-Retrieval: End-to-End Information Retrieval with One Large Language Model

2 code implementations23 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.

Information Retrieval Language Modeling +4

Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?

no code implementations22 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.

Hidding the Ghostwriters: An Adversarial Evaluation of AI-Generated Student Essay Detection

1 code implementation1 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.

Sentence Text Generation

Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting

no code implementations22 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).

Hallucination Language Modeling +2

Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval

1 code implementation20 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.

Information Retrieval Retrieval

Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection

no code implementations31 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.

Adversarial Attack Information Retrieval +2

Understanding Differential Search Index for Text Retrieval

1 code implementation3 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.

Information Retrieval Text Retrieval

Towards Imperceptible Document Manipulations against Neural Ranking Models

no code implementations3 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.

Adversarial Text Language Modeling +2

Groupwise Query Performance Prediction with BERT

1 code implementation25 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.

Learning-To-Rank Re-Ranking

Co-BERT: A Context-Aware BERT Retrieval Model Incorporating Local and Query-specific Context

no code implementations17 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.

Learning-To-Rank Re-Ranking +1

Global Bootstrapping Neural Network for Entity Set Expansion

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.

Decoder

Simplified TinyBERT: Knowledge Distillation for Document Retrieval

4 code implementations16 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.

Document Ranking Knowledge Distillation +1

PARADE: Passage Representation Aggregation for Document Reranking

1 code implementation20 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.

Document Ranking Knowledge Distillation

Learning to Bootstrap for Entity Set Expansion

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.

Image Captioning based on Deep Learning Methods: A Survey

no code implementations20 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.

Decoder Deep Learning +4

NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval

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.

Ad-Hoc Information Retrieval Information Retrieval +1

Cannot find the paper you are looking for? You can Submit a new open access paper.