paper-with-me

홈 › Papers

GenDec: A robust generative Question-decomposition method for Multi-hop reasoning

2024-02-17 · Jian Wu, Linyi Yang, Yuliang Ji, Wenhao Huang, Börje F. Karlsson, Manabu Okumura

Multi-hop QA (MHQA) involves step-by-step reasoning to answer complex questions and find multiple relevant supporting facts. However, Existing large language models'(LLMs) reasoning ability in multi-hop question answering remains exploration, which is inadequate in answering multi-hop questions. Moreover, it is unclear whether LLMs follow a desired reasoning chain to reach the right final answer. In this paper, we propose a \textbf{gen}erative question \textbf{dec}omposition method (GenDec) from the perspective of explainable QA by generating independent and complete sub-questions based on incorporating additional extracted evidence for enhancing LLMs' reasoning ability in RAG. To demonstrate the impact, generalization, and robustness of Gendec, we conduct two experiments, the first is combining GenDec with small QA systems on paragraph retrieval and QA tasks. We secondly examine the reasoning capabilities of various state-of-the-art LLMs including GPT-4 and GPT-3.5 combined with GenDec. We experiment on the HotpotQA, 2WikihopMultiHopQA, MuSiQue, and PokeMQA datasets.

📄 PDF Abstract BibTeX arXiv:2402.11166

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-hop Question AnsweringQuestion AnsweringRAGRetrieval

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
WordPiece 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

2018-03-21 · ECCV 2018 9 · Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang 외

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue…

3D Pose EstimationPose Estimation

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

2020-04-15 · Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang 외

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the e…

DenoisingPose Estimation

On the Statistical Complexity of Estimating VENDI Scores from Empirical Data

2024-10-29 · Azim Ospanov, Farzan Farnia

Reference-free evaluation metrics for generative models have recently been studied in the machine learning community. As a reference-free metric, the VENDI score quantifies the diversity of generative models using matrix…

Diversity

Optimally adaptive Bayesian spectral density estimation for stationary and nonstationary processes

2020-03-04 · Nick James, Max Menzies

This article improves on existing methods to estimate the spectral density of stationary and nonstationary time series assuming a Gaussian process prior. By optimising an appropriate eigendecomposition using a smoothing …

Density EstimationTime SeriesTime Series Analysis

Accelerated graph-based spectral polynomial filters

2015-09-08 · Andrew Knyazev, Alexander Malyshev

Graph-based spectral denoising is a low-pass filtering using the eigendecomposition of the graph Laplacian matrix of a noisy signal. Polynomial filtering avoids costly computation of the eigendecomposition by projections…

Denoising