23 citations · 98 across the 68 of their papers we have counts for
28 papers · 1 filter
MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning
Nianqi Li, Zujie Liang, Siyu Yuan +3
Program-of-Thought (PoT), which aims to use programming language instead of natural language as an intermediate step in reasoning, is an important way for LLMs to solve mathematica…
EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data
Xuetian Chen, Hangcheng Li, Jiaqing Liang +2
Autonomous agents operating on the graphical user interfaces (GUIs) of various applications hold immense practical value. Unlike the large language model (LLM)-based methods which…
QUILL: Quotation Generation Enhancement of Large Language Models
Jin Xiao, Bowei Zhang, Qianyu He +6
While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing f…
Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
Chengyu Du, Jinyi Han, Yizhou Ying +9
Recent advancements in large language models (LLMs) have demonstrated that progressive refinement, rather than providing a single answer, results in more accurate and thoughtful ou…
SEGMENT+: Long Text Processing with Short-Context Language Models
Wei Shi, Shuang Li, Kerun Yu +9
There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust…
Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?
Yuyan Chen, Tianhao Yu, Yueze Li +4
The evaluation of the problem-solving capability under incomplete information scenarios of Large Language Models (LLMs) is increasingly important, encompassing capabilities such as…
Past Meets Present: Creating Historical Analogy with Large Language Models
Nianqi Li, Siyu Yuan, Jiangjie Chen +5
Historical analogies, which compare known past events with contemporary but unfamiliar events, are important abilities that help people make decisions and understand the world. How…
Can Pre-trained Language Models Understand Chinese Humor?
Yuyan Chen, Zhixu Li, Jiaqing Liang +3
Humor understanding is an important and challenging research in natural language processing. As the popularity of pre-trained language models (PLMs), some recent work makes prelimi…
Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Sirui Xia, Xintao Wang, Jiaqing Liang +5
Retrieval-Augmented Generation (RAG) has been widely adopted to enhance Large Language Models (LLMs) in knowledge-intensive tasks. To enhance credibility and verifiability in RAG s…
Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
Yifei Zhang, Xintao Wang, Jiaqing Liang +3
Large Language Models (LLMs) have exhibited impressive proficiency in various natural language processing (NLP) tasks, which involve increasingly complex reasoning. Knowledge reaso…
Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models
Yikai Zhang, Qianyu He, Xintao Wang +3
Multi-Modal Knowledge Graphs (MMKGs) have proven valuable for various downstream tasks. However, scaling them up is challenging because building large-scale MMKGs often introduces…
Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals
Lida Chen, Zujie Liang, Xintao Wang +7
Large language models (LLMs) have achieved great success, but their occasional content fabrication, or hallucination, limits their practical application. Hallucination arises becau…
Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data
Yiting Ran, Xintao Wang, Rui Xu +4
Role-playing agents (RPA) have been a popular application area for large language models (LLMs), attracting significant interest from both industry and academia.While existing RPAs…
Adaptive Reinforcement Learning Planning: Harnessing Large Language Models for Complex Information Extraction
Zepeng Ding, Ruiyang Ke, Wenhao Huang +4
Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex…
SED: Self-Evaluation Decoding Enhances Large Language Models for Better Generation
Ziqin Luo, Haixia Han, Haokun Zhao +6
Existing Large Language Models (LLMs) generate text through unidirectional autoregressive decoding methods to respond to various user queries. These methods tend to consider token…
Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
Dixuan Wang, Yanda Li, Junyuan Jiang +5
Large Language Models (LLMs) have shown remarkable capabilities in language understanding and generation. Nonetheless, it was also witnessed that LLMs tend to produce inaccurate re…
Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience
Haixia Han, Tingyun Li, Shisong Chen +5
Large Language Models (LLMs) have exhibited remarkable performance across various downstream tasks, but they may generate inaccurate or false information with a confident tone. One…
Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction
Zepeng Ding, Wenhao Huang, Jiaqing Liang +2
Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples fr…
Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
Yanda Li, Dixuan Wang, Jiaqing Liang +4
Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but they still struggle with some complicated reasoning tasks including logical reasoning.…
From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
Qianyu He, Jie Zeng, Qianxi He +2
It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to en…
AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation
Wenhao Huang, Zhouhong Gu, Chenghao Peng +5
Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry ef…
Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?
Rui Xu, Xintao Wang, Jiangjie Chen +6
Can Large Language Models (LLMs) simulate humans in making important decisions? Recent research has unveiled the potential of using LLMs to develop role-playing language agents (RP…
ToNER: Type-oriented Named Entity Recognition with Generative Language Model
Guochao Jiang, Ziqin Luo, Yuchen Shi +3
In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has…
CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes
Haokun Zhao, Haixia Han, Jie Shi +3
As world knowledge advances and new task schemas emerge, Continual Learning (CL) becomes essential for keeping Large Language Models (LLMs) current and addressing their shortcoming…