Search Results for author: Keming Lu

Found 17 papers, 11 papers with code

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

1 code implementation23 Jan 2024 Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou

Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora.

Instruction Following Reading Comprehension

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

no code implementations15 Nov 2023 Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou

Zooter shows computation efficiency in inference as it introduces only a minor computation overhead of a routing function compared with reward model ranking methods.

TAG

Speculative Contrastive Decoding

no code implementations15 Nov 2023 Hongyi Yuan, Keming Lu, Fei Huang, Zheng Yuan, Chang Zhou

We proposed Speculative Contrastive Decoding (SCD), an accelerated decoding method leveraging the natural contrast between expert and amateur models in speculative decoding.

Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning

1 code implementation14 Nov 2023 Shengguang Wu, Keming Lu, Benfeng Xu, Junyang Lin, Qi Su, Chang Zhou

The key to our data sampling technique lies in the enhancement of diversity in the chosen subsets, as the model selects new data points most distinct from any existing ones according to its current embedding space.

Instruction Following

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

no code implementations9 Oct 2023 Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies.

Code Generation Instruction Following +2

Query and Response Augmentation Cannot Help Out-of-domain Math Reasoning Generalization

1 code implementation9 Oct 2023 Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou

In this paper, we conduct an investigation for such data augmentation in math reasoning and are intended to answer: (1) What strategies of data augmentation are more effective; (2) What is the scaling relationship between the amount of augmented data and model performance; and (3) Can data augmentation incentivize generalization to out-of-domain mathematical reasoning tasks?

Ranked #44 on Arithmetic Reasoning on GSM8K (using extra training data)

Arithmetic Reasoning Data Augmentation +3

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

1 code implementation14 Aug 2023 Keming Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, Jingren Zhou

Based on this observation, we propose a data selector based on InsTag to select 6K diverse and complex samples from open-source datasets and fine-tune models on InsTag-selected data.

Instruction Following TAG

Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

1 code implementation3 Aug 2023 Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Keming Lu, Chuanqi Tan, Chang Zhou, Jingren Zhou

We find with augmented samples containing more distinct reasoning paths, RFT improves mathematical reasoning performance more for LLMs.

Ranked #79 on Arithmetic Reasoning on GSM8K (using extra training data)

Arithmetic Reasoning GSM8K +1

PIVOINE: Instruction Tuning for Open-world Information Extraction

1 code implementation24 May 2023 Keming Lu, Xiaoman Pan, Kaiqiang Song, Hongming Zhang, Dong Yu, Jianshu Chen

In particular, we construct INSTRUCTOPENWIKI, a substantial instruction tuning dataset for Open-world IE enriched with a comprehensive corpus, extensive annotations, and diverse instructions.

Instruction Following Language Modelling +1

Exploring Partial Knowledge Base Inference in Biomedical Entity Linking

1 code implementation18 Mar 2023 Hongyi Yuan, Keming Lu, Zheng Yuan

Biomedical entity linking (EL) consists of named entity recognition (NER) and named entity disambiguation (NED).

Entity Disambiguation Entity Linking +3

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

1 code implementation21 Dec 2022 Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen

Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document.

Relation Relation Extraction +1

Knowledge-Enhanced Relation Extraction Dataset

no code implementations19 Oct 2022 Yucong Lin, Hongming Xiao, Jiani Liu, Zichao Lin, Keming Lu, Feifei Wang, Wei Wei

Recently, knowledge-enhanced methods leveraging auxiliary knowledge graphs have emerged in relation extraction, surpassing traditional text-based approaches.

Entity Linking Knowledge Graphs +3

Summarization as Indirect Supervision for Relation Extraction

1 code implementation19 May 2022 Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen

Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context, these tasks naturally align with the objective of RE, i. e., extracting a kind of synoptical information that describes the relation of entity mentions.

Relation Relation Extraction +1

BIOS: An Algorithmically Generated Biomedical Knowledge Graph

no code implementations18 Mar 2022 Sheng Yu, Zheng Yuan, Jun Xia, Shengxuan Luo, Huaiyuan Ying, Sihang Zeng, Jingyi Ren, Hongyi Yuan, Zhengyun Zhao, Yucong Lin, Keming Lu, Jing Wang, Yutao Xie, Heung-Yeung Shum

For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary.

BIG-bench Machine Learning Knowledge Graphs +3

Multimodal Learning on Graphs for Disease Relation Extraction

1 code implementation16 Mar 2022 Yucong Lin, Keming Lu, Sheng Yu, Tianxi Cai, Marinka Zitnik

On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10. 0% (accuracy) and 17. 2% (F1-score) by fusing disease knowledge graphs with text information.

Knowledge Graphs Relation +1

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