arXiv subjects

Shicheng Liu

Publications and source records attributed to Shicheng Liu.

25 records · Page 2Linked to original sources

arXiv2024

SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing

We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge base, text, tables, and infoboxes. Our LLM-augmented approach achieves state-of-the-art performance on the Compmix dataset, the most comprehensive heterogeneous open-domain QA dataset, with 56.5% exact match (EM) rate. More importantly, manual analysis on a sample of the dataset suggests that SPAGHETTI is more than 90% accurate, indicating that EM is no longer suitable for assessing the capabilities of QA systems today.

cs.CL↗

arXiv2024

Convergence analysis of a weak Galerkin finite element method on a Bakhvalov-type mesh for a singularly perturbed convection-diffusion equation in 2D

In this paper, we propose a weak Galerkin finite element method (WG) for solving singularly perturbed convection-diffusion problems on a Bakhvalov-type mesh in 2D. Our method is flexible and allows the use of discontinuous approximation functions on the meshe. An error estimate is devised in a suitable norm and the optimal convergence order is obtained. Finally, numerical experiments are given to support the theory and to show the efficiency of the proposed method.

math.NA↗

arXiv2024

Convergence analysis of a weak Galerkin finite element method on a Shishkin mesh for a singularly perturbed fourth-order problem in 2D

We consider the singularly perturbed fourth-order boundary value problem $\varepsilon ^{2}Δ^{2}u-Δu=f $ on the unit square $Ω\subset \mathbb{R}^2$, with boundary conditions $u = \partial u / \partial n = 0$ on $\partial Ω$, where $\varepsilon \in (0, 1)$ is a small parameter. The problem is solved numerically by means of a weak Galerkin(WG) finite element method, which is highly robust and flexible in the element construction by using discontinuous piecewise polynomials on finite element partitions consisting of polygons of arbitrary shape. The resulting WG finite element formulation is symmetric, positive definite, and parameter-free. Under reasonable assumptions on the structure of the boundary layers that appear in the solution, a family of suitable Shishkin meshes with $N^2$ elements is constructed ,convergence of the method is proved in a discrete $H^2$ norm for the corresponding WG finite element solutions and numerical results are presented.

math.NA↗

arXiv2024

The stabilizer free weak Galerkin mixed finite elements method for the biharmonic equation

In this article, the stabilizer free weak Galerkin (SFWG) finite element method is applied to the Ciarlet-Raviart mixed form of the Biharmonic equation. We utilize the SFWG solutions of the second elliptic problems to define projection operators, build error equations, and further derive the error estimates. Finally, numerical examples support the results reached by the theory.

math.NA↗

arXiv2024

SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models

While most conversational agents are grounded on either free-text or structured knowledge, many knowledge corpora consist of hybrid sources. This paper presents the first conversational agent that supports the full generality of hybrid data access for large knowledge corpora, through a language we developed called SUQL (Structured and Unstructured Query Language). Specifically, SUQL extends SQL with free-text primitives (summary and answer), so information retrieval can be composed with structured data accesses arbitrarily in a formal, succinct, precise, and interpretable notation. With SUQL, we propose the first semantic parser, an LLM with in-context learning, that can handle hybrid data sources. Our in-context learning-based approach, when applied to the HybridQA dataset, comes within 8.9% exact match and 7.1% F1 of the SOTA, which was trained on 62K data samples. More significantly, unlike previous approaches, our technique is applicable to large databases and free-text corpora. We introduce a dataset consisting of crowdsourced questions and conversations on Yelp, a large, real restaurant knowledge base with structured and unstructured data. We show that our few-shot conversational agent based on SUQL finds an entity satisfying all user requirements 90.3% of the time, compared to 63.4% for a baseline based on linearization.

cs.CL↗

arXiv2023

Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata

While large language models (LLMs) can answer many questions correctly, they can also hallucinate and give wrong answers. Wikidata, with its over 12 billion facts, can be used to ground LLMs to improve their factuality. This paper presents WikiWebQuestions, a high-quality question answering benchmark for Wikidata. Ported over from WebQuestions for Freebase, it consists of real-world data with SPARQL annotation. This paper presents a few-shot sequence-to-sequence semantic parser for Wikidata. We modify SPARQL to use the unique domain and property names instead of their IDs. We train the parser to use either the results from an entity linker or mentions in the query. We fine-tune LLaMA by adding the few-shot training data to that used to fine-tune Alpaca. Our experimental results demonstrate the effectiveness of this methodology, establishing a strong baseline of 76% and 65% answer accuracy in the dev and test sets of WikiWebQuestions, respectively. By pairing our semantic parser with GPT-3, we combine verifiable results with qualified GPT-3 guesses to provide useful answers to 96% of the questions in dev. We also show that our method outperforms the state-of-the-art for the QALD-7 Wikidata dataset by 3.6% in F1 score.

cs.CL↗

arXiv2019

Strong Aharonov-Bohm quantum interference in simply-connected LaAlO$_3$/SrTiO$_3$ structures

We report Aharonov-Bohm (AB)-type quantum interference in simply-connected devices created at the LaAlO$_3$/SrTiO$_3$ interface using conductive-atomic force microscope (c-AFM) lithography. The oscillations are multi-periodic functions of magnetic field strength, and they exhibit a substantial magnetic hysteresis with frequencies that depends on the magnetic sweep direction. The oscillation amplitude for the lowest two frequencies approaches $e^2/h$, consistent with the theoretical maximum for the AB effect, and harmonics up to third order are observable. Broadband quasiperiodic behavior is reported in a fraction of simply-connected electron waveguide devices that exhibit magnetic asymmetries. Curiously, nanoscale ring devices that are multiply-connected lack signatures of AB quantum interference. The interference phenomena are associated with an inhomogeneous magnetic landscape within the LaAlO$_3$/SrTiO$_3$ nanostructures.

cond-mat.mes-hall↗