A-Long Jin
YOU?
Author Swipe
View article: TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions Open
Large Vision-Language Models (LVLMs) have achieved remarkable progress on visual perception and linguistic interpretation. Despite their impressive capabilities across various tasks, LVLMs still suffer from the issue of hallucination, whic…
View article: Improving Factual Error Correction by Learning to Inject Factual Errors
Improving Factual Error Correction by Learning to Inject Factual Errors Open
Factual error correction (FEC) aims to revise factual errors in false claims with minimal editing, making them faithful to the provided evidence. This task is crucial for alleviating the hallucination problem encountered by large language …
View article: Improving Factual Error Correction by Learning to Inject Factual Errors
Improving Factual Error Correction by Learning to Inject Factual Errors Open
Factual error correction (FEC) aims to revise factual errors in false claims with minimal editing, making them faithful to the provided evidence. This task is crucial for alleviating the hallucination problem encountered by large language …
View article: AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators
AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators Open
Many natural language processing (NLP) tasks rely on labeled data to train machine learning models with high performance. However, data annotation is time-consuming and expensive, especially when the task involves a large amount of data or…
View article: PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models
PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models Open
Factual Error Correction (FEC) aims to rectify false claims by making minimal revisions to align them more accurately with supporting evidence. However, the lack of datasets containing false claims and their corresponding corrections has i…
View article: CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion
CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion Open
The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and docu…
View article: CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion
CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion Open
The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and docu…
View article: Development and functional design of the test device for induced voltage in distribution network lines
Development and functional design of the test device for induced voltage in distribution network lines Open
In order to measure the induced voltage of the suspended conductor under the high-voltage transmission line, a portable floating potential measuring device is developed in this paper. This paper proposes a design scheme and develops a high…
View article: Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning
Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning Open
Commonsense generation aims to generate a realistic sentence describing a daily scene under the given concepts, which is very challenging, since it requires models to have relational reasoning and compositional generalization capabilities.…
View article: Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning
Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning Open
Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, Sm Yiu, Nan Duan. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.
View article: LBFA: A Load-Balanced and Fragmentation-Aware Resource Allocation Algorithm in Space-Division Multiplexing Elastic Optical Networks
LBFA: A Load-Balanced and Fragmentation-Aware Resource Allocation Algorithm in Space-Division Multiplexing Elastic Optical Networks Open
We consider a space-division multiplexing elastic optical network (SDM-EON) that supports super-channels (SChs). A Sch comprises a set of contiguous frequency slots on multiple cores in a multi-core fiber. The problem of finding a lightpat…