中文
相关论文

相关论文: Conv-CoA: Improving Open-domain Question Answering…

200 篇论文

We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is…

计算与语言 · 计算机科学 2025-02-24 Zhenyu Pan , Haozheng Luo , Manling Li , Han Liu

Open-Domain Conversational Question Answering (ODConvQA) aims at answering questions through a multi-turn conversation based on a retriever-reader pipeline, which retrieves passages and then predicts answers with them. However, such a…

计算与语言 · 计算机科学 2023-06-08 Soyeong Jeong , Jinheon Baek , Sung Ju Hwang , Jong C. Park

Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate passages from a large corpus and the latter requires better…

计算与语言 · 计算机科学 2022-11-18 Hung-Chieh Fang , Kuo-Han Hung , Chao-Wei Huang , Yun-Nung Chen

Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either…

信息检索 · 计算机科学 2020-05-26 Chen Qu , Liu Yang , Cen Chen , Minghui Qiu , W. Bruce Croft , Mohit Iyyer

Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have shown impressive reasoning ability in various downstream tasks. Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come…

计算与语言 · 计算机科学 2023-10-31 Keheng Wang , Feiyu Duan , Sirui Wang , Peiguang Li , Yunsen Xian , Chuantao Yin , Wenge Rong , Zhang Xiong

While recent work has extended CoT to multimodal settings, achieving state-of-the-art results on science question answering benchmarks like ScienceQA, the generalizability of these approaches across diverse domains remains underexplored.…

人工智能 · 计算机科学 2025-11-27 Nitya Tiwari , Parv Maheshwari , Vidisha Agarwal

Humans gather information by engaging in conversations involving a series of interconnected questions and answers. For machines to assist in information gathering, it is therefore essential to enable them to answer conversational questions.…

计算与语言 · 计算机科学 2019-04-02 Siva Reddy , Danqi Chen , Christopher D. Manning

We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources. The key novelty of our method is the introduction of the intermediary modules into the…

计算与语言 · 计算机科学 2022-10-25 Kaixin Ma , Hao Cheng , Xiaodong Liu , Eric Nyberg , Jianfeng Gao

Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their…

计算与语言 · 计算机科学 2023-09-26 Shehzaad Dhuliawala , Mojtaba Komeili , Jing Xu , Roberta Raileanu , Xian Li , Asli Celikyilmaz , Jason Weston

Recent studies on Question Answering (QA) and Conversational QA (ConvQA) emphasize the role of retrieval: a system first retrieves evidence from a large collection and then extracts answers. This open-retrieval ConvQA setting typically…

信息检索 · 计算机科学 2021-03-04 Chen Qu , Liu Yang , Cen Chen , W. Bruce Croft , Kalpesh Krishna , Mohit Iyyer

Open-domain question answering (OpenQA) is an important branch of textual QA which discovers answers for the given questions based on a large number of unstructured documents. Effectively mining correct answers from the open-domain sources…

计算与语言 · 计算机科学 2022-04-04 Tingting Liang , Yixuan Jiang , Congying Xia , Ziqiang Zhao , Yuyu Yin , Philip S. Yu

Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB),…

信息检索 · 计算机科学 2023-07-03 Philipp Christmann , Rishiraj Saha Roy , Gerhard Weikum

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and…

计算与语言 · 计算机科学 2025-08-28 Anant Khandelwal , Manish Gupta , Puneet Agrawal

Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by…

计算与语言 · 计算机科学 2024-06-06 Yusen Zhang , Ruoxi Sun , Yanfei Chen , Tomas Pfister , Rui Zhang , Sercan Ö. Arik

Open domain question answering (ODQA) is a longstanding task aimed at answering factual questions from a large knowledge corpus without any explicit evidence in natural language processing (NLP). Recent works have predominantly focused on…

计算与语言 · 计算机科学 2022-11-16 Qin Zhang , Shangsi Chen , Dongkuan Xu , Qingqing Cao , Xiaojun Chen , Trevor Cohn , Meng Fang

Large Language Models have demonstrated remarkable abilities across various tasks, with Chain-of-Thought (CoT) prompting emerging as a key technique to enhance reasoning capabilities. However, existing research primarily focuses on…

人工智能 · 计算机科学 2024-10-07 Lijie Hu , Liang Liu , Shu Yang , Xin Chen , Zhen Tan , Muhammad Asif Ali , Mengdi Li , Di Wang

Large language models (LLMs) have shown impressive performance on complex reasoning by leveraging chain-of-thought (CoT) prompting to generate intermediate reasoning chains as the rationale to infer the answer. However, existing CoT studies…

计算与语言 · 计算机科学 2024-05-21 Zhuosheng Zhang , Aston Zhang , Mu Li , Hai Zhao , George Karypis , Alex Smola

The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues…

计算与语言 · 计算机科学 2020-09-08 Jon Ander Campos , Arantxa Otegi , Aitor Soroa , Jan Deriu , Mark Cieliebak , Eneko Agirre

Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both efficiency and effectiveness. In this paper, we study the…

计算与语言 · 计算机科学 2023-10-24 Andrei C. Coman , Gianni Barlacchi , Adrià de Gispert

Reasoning capabilities in large language models (LLMs) have substantially advanced through methods such as chain-of-thought and explicit step-by-step explanations. However, these improvements have not yet fully transitioned to multimodal…

计算与语言 · 计算机科学 2025-08-07 Nima Iji , Kia Dashtipour
‹ 上一页 1 2 3 10 下一页 ›