Search Results for author: Ante Wang

Found 12 papers, 8 papers with code

A Dual-Perspective Metaphor Detection Framework Using Large Language Models

1 code implementation23 Dec 2024 Yujie Lin, Jingyao Liu, Yan Gao, Ante Wang, Jinsong Su

Metaphor detection, a critical task in natural language processing, involves identifying whether a particular word in a sentence is used metaphorically.

Decision Making Knowledge Graphs +1

Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation

1 code implementation29 Oct 2024 Suhang Wu, Jialong Tang, Baosong Yang, Ante Wang, Kaidi Jia, Jiawei Yu, Junfeng Yao, Jinsong Su

Experimental results reveal linguistic inequalities: 1) high-resource languages stand out in Monolingual Knowledge Extraction; 2) Indo-European languages lead RALMs to provide answers directly from documents, alleviating the challenge of expressing answers across languages; 3) English benefits from RALMs' selection bias and speaks louder in multilingual knowledge selection.

Retrieval Selection bias +1

Mitigating the Negative Impact of Over-association for Conversational Query Production

1 code implementation29 Sep 2024 Ante Wang, Linfeng Song, Zijun Min, Ge Xu, Xiaoli Wang, Junfeng Yao, Jinsong Su

We carefully analyze the negative effects of this phenomenon on pretrained Seq2seq query producers and then propose effective instance-level weighting strategies for training to mitigate these issues from multiple perspectives.

Attribute

LiteSearch: Efficacious Tree Search for LLM

no code implementations29 Jun 2024 Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Dian Yu, Haitao Mi, Jinsong Su, Dong Yu

Recent research suggests that tree search algorithms (e. g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks.

GSM8K Mathematical Reasoning

Self-Consistency Boosts Calibration for Math Reasoning

no code implementations14 Mar 2024 Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu

Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development.

GSM8K Math

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

1 code implementation2 Mar 2024 Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su

When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent.

Continual Learning In-Context Learning

Fine-Grained Self-Endorsement Improves Factuality and Reasoning

no code implementations23 Feb 2024 Ante Wang, Linfeng Song, Baolin Peng, Ye Tian, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu

Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.

GSM8K Language Modeling +3

Response Enhanced Semi-supervised Dialogue Query Generation

1 code implementation20 Dec 2023 Jianheng Huang, Ante Wang, Linfeng Gao, Linfeng Song, Jinsong Su

Based on the observation that the search query is typically related to the topic of dialogue response, we train a response-augmented query producer (RA) to provide rich and effective training signals for QP.

Domain Adaptation

Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production

1 code implementation16 Feb 2023 Ante Wang, Linfeng Song, Qi Liu, Haitao Mi, Longyue Wang, Zhaopeng Tu, Jinsong Su, Dong Yu

We propose a dialogue model that can access the vast and dynamic information from any search engine for response generation.

Chatbot Response Generation

BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation

no code implementations ACL 2021 Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, Jana Diesner

In this paper, we focus on the problem of citing sentence generation, which entails generating a short text to capture the salient information in a cited paper and the connection between the citing and cited paper.

Sentence Text Generation

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