193 citations · 656 across the 39 of their papers we have counts for
41 papers
From Context to Skills: Can Language Models Learn from Context Skillfully?
Shuzheng Si, Haozhe Zhao, Yu Lei +10
Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly lear…
InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
Yuzhuo Bai, Shuzheng Si, Kangyang Luo +5
Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretab…
From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition
Yiqing Zhou, Yu Lei, Shuzheng Si +7
Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents…
FaithLens: Detecting and Explaining Faithfulness Hallucination
Shuzheng Si, Qingyi Wang, Haozhe Zhao +8
Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and su…
RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
Yu Lei, Shuzheng Si, Wei Wang +4
Large language models are evolving from single-turn responders into tool-using agents capable of sustained reasoning and decision-making for deep research. Prevailing systems adopt…
A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
Shuzheng Si, Haozhe Zhao, Kangyang Luo +5
Agents based on large language models (LLMs) struggle with brainless trial-and-error and generating hallucinatory actions due to a lack of global planning in long-horizon tasks. In…
WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
Ran Wang, Xiaoxuan Liu, Hao Ren +3
Structured decoding enables large language models (LLMs) to generate outputs in formats required by downstream systems, such as HTML or JSON. However, existing methods suffer from…
Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
Shuzheng Si, Haozhe Zhao, Cheng Gao +11
Teaching large language models (LLMs) to be faithful in the provided context is crucial for building reliable information-seeking systems. Therefore, we propose a systematic framew…
Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
Shuzheng Si, Haozhe Zhao, Gang Chen +9
Training LLMs on data containing unfamiliar knowledge during the instruction tuning stage can encourage hallucinations. To address this challenge, we introduce NOVA, a novel framew…
GATEAU: Selecting Influential Samples for Long Context Alignment
Shuzheng Si, Haozhe Zhao, Gang Chen +7
Aligning large language models to handle instructions with extremely long contexts has yet to be fully investigated. Previous studies have attempted to scale up the available data…
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
Yujia Qin, Zihan Cai, Dian Jin +12
Long-form question answering (LFQA) aims at answering complex, open-ended questions with detailed, paragraph-length responses. The de facto paradigm of LFQA necessitates two proced…
C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu +10
New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite desi…
Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP
Yangyi Chen, Hongcheng Gao, Ganqu Cui +4
Textual adversarial samples play important roles in multiple subfields of NLP research, including security, evaluation, explainability, and data augmentation. However, most work mi…
Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information
Fanchao Qi, Chuancheng Lv, Zhiyuan Liu +3
In linguistics, a sememe is defined as the minimum semantic unit of languages. Sememe knowledge bases (KBs), which are built by manually annotating words with sememes, have been su…
QuoteR: A Benchmark of Quote Recommendation for Writing
Fanchao Qi, Yanhui Yang, Jing Yi +3
It is very common to use quotations (quotes) to make our writings more elegant or convincing. To help people find appropriate quotes efficiently, the task of quote recommendation i…
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Yuan Yao, Qingxiu Dong, Jian Guan +32
Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding ro…
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer
Fanchao Qi, Yangyi Chen, Xurui Zhang +3
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation…
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks
Yangyi Chen, Fanchao Qi, Hongcheng Gao +2
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give…
CPM-2: Large-scale Cost-effective Pre-trained Language Models
Zhengyan Zhang, Yuxian Gu, Xu Han +16
In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-…
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
Fanchao Qi, Yuan Yao, Sophia Xu +2
Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but…
CCPM: A Chinese Classical Poetry Matching Dataset
Wenhao Li, Fanchao Qi, Maosong Sun +2
Poetry is one of the most important art forms of human languages. Recently many studies have focused on incorporating some linguistic features of poetry, such as style and sentimen…
Automatic Construction of Sememe Knowledge Bases via Dictionaries
Fanchao Qi, Yangyi Chen, Fengyu Wang +3
A sememe is defined as the minimum semantic unit in linguistics. Sememe knowledge bases (SKBs), which comprise words annotated with sememes, enable sememes to be applied to natural…
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger
Fanchao Qi, Mukai Li, Yangyi Chen +4
Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-…
Sub-Character Tokenization for Chinese Pretrained Language Models
Chenglei Si, Zhengyan Zhang, Yingfa Chen +6
Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, th…