4 citations · 9 across the 11 of their papers we have counts for
11 papers
Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
Shicheng Fan, Haochang Hao, Dehai Min +10
Process supervision during reinforcement learning (RL) post-training matters in factual question answering (QA) because responses receiving positive response-level rewards can stil…
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Weihao Liu, Dehai Min, Lu Cheng
While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Rec…
MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads
Weihao Liu, Ning Wu, Shiping Yang +4
Large Language Models (LLMs) frequently show distracted attention due to irrelevant information in the input, which severely impairs their long-context capabilities. Inspired by re…
Selected Languages are All You Need for Cross-lingual Truthfulness Transfer
Weihao Liu, Ning Wu, Wenbiao Ding +3
Truthfulness stands out as an essential challenge for Large Language Models (LLMs). Although many works have developed various ways for truthfulness enhancement, they seldom focus…
SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inference
Yanming Liu, Xinyue Peng, Ningjing Sang +10
Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require substantial memory storage on low-resource devices.…
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
Yanming Liu, Xinyue Peng, Tianyu Du +3
Large language models (LLMs) have achieved commendable accomplishments in various natural language processing tasks. However, LLMs still encounter significant challenges when deali…
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Yanming Liu, Xinyue Peng, Xuhong Zhang +4
Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge…
MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models
Tongxu Luo, Jiahe Lei, Fangyu Lei +4
Fine-tuning is often necessary to enhance the adaptability of Large Language Models (LLM) to downstream tasks. Nonetheless, the process of updating billions of parameters demands s…
TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering
Fangyu Lei, Tongxu Luo, Pengqi Yang +8
Table-based question answering (TableQA) is an important task in natural language processing, which requires comprehending tables and employing various reasoning ways to answer the…
HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering
Tongxu Luo, Fangyu Lei, Jiahe Lei +4
Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task. Recently, Large Language Models (LLMs) have gained significant…
MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images
Weihao Liu, Fangyu Lei, Tongxu Luo +4
In the real world, knowledge often exists in a multimodal and heterogeneous form. Addressing the task of question answering with hybrid data types, including text, tables, and imag…