arXiv subjects

Minghui Huang

Publications and source records attributed to Minghui Huang.

6 recordsLinked to original sources

arXiv2026

Atomic-SNLI: Fine-Grained Natural Language Inference through Atomic Fact Decomposition

Current Natural Language Inference (NLI) systems primarily operate at the sentence level, providing black-box decisions that lack explanatory power. While atomic-level NLI offers a promising alternative by decomposing hypotheses into individual facts, we demonstrate that the conventional assumption that a hypothesis is entailed only when all its atomic facts are entailed fails in practice due to models' poor performance on fine-grained reasoning. Our analysis reveals that existing models perform substantially worse on atomic level inference compared to sentence level tasks. To address this limitation, we introduce Atomic-SNLI, a novel dataset constructed by decomposing SNLI and enriching it with carefully curated atomic level examples through linguistically informed generation strategies. Experimental results demonstrate that models fine-tuned on Atomic-SNLI achieve significant improvements in atomic reasoning capabilities while maintaining strong sentence level performance, enabling both accurate judgements and transparent, explainable results at the fact level.

cs.CL↗

arXiv2025

DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs

Claim decomposition plays a crucial role in the fact-checking process by breaking down complex claims into simpler atomic components and identifying their unfactual elements. Despite its importance, current research primarily focuses on generative methods for decomposition, with insufficient emphasis on evaluating the quality of these decomposed atomic claims. To bridge this gap, we introduce \textbf{DecMetrics}, which comprises three new metrics: \texttt{COMPLETENESS}, \texttt{CORRECTNESS}, and \texttt{SEMANTIC ENTROPY}, designed to automatically assess the quality of claims produced by decomposition models. Utilizing these metrics, we develop a lightweight claim decomposition model, optimizing its performance through the integration of these metrics as a reward function. Through automatic evaluation, our approach aims to set a benchmark for claim decomposition, enhancing both the reliability and effectiveness of fact-checking systems.

cs.CL↗

arXiv2025

PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism

Recent graph-based RAG approaches leverage knowledge graphs by extracting entities from a query to fetch their associated relationships and metadata. However, relying solely on entity extraction often results in the misinterpretation or omission of latent critical information and relationships. This can lead to the retrieval of irrelevant or contradictory content, as well as the exclusion of essential information, thereby increasing hallucination risks and undermining the quality of generated responses. In this paper, we propose PankRAG, a framework designed to capture and resolve the latent relationships within complex queries that prior methods overlook. It achieves this through a synergistic combination of a globally-aware hierarchical resolution pathway and a dependency-aware reranking mechanism. PankRAG first generates a globally aware resolution pathway that captures parallel and progress relationships, guiding LLMs to resolve queries through a hierarchical reasoning path. Additionally, its dependency-aware reranking mechanism utilizes resolved sub-question dependencies to augment and validate the retrieved content of the current unresolved sub-question. Experimental results demonstrate that PankRAG consistently outperforms existing state-of-the-art methods, underscoring its generalizability.

cs.CL↗

arXiv2021

GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback

Query expansion with pseudo-relevance feedback (PRF) is a powerful approach to enhance the effectiveness in information retrieval. Recently, with the rapid advance of deep learning techniques, neural text generation has achieved promising success in many natural language tasks. To leverage the strength of text generation for information retrieval, in this article, we propose a novel approach which effectively integrates text generation models into PRF-based query expansion. In particular, our approach generates augmented query terms via neural text generation models conditioned on both the initial query and pseudo-relevance feedback. Moreover, in order to train the generative model, we adopt the conditional generative adversarial nets (CGANs) and propose the PRF-CGAN method in which both the generator and the discriminator are conditioned on the pseudo-relevance feedback. We evaluate the performance of our approach on information retrieval tasks using two benchmark datasets. The experimental results show that our approach achieves comparable performance or outperforms traditional query expansion methods on both the retrieval and reranking tasks.

cs.IR↗

arXiv2021

TPRM: A Topic-based Personalized Ranking Model for Web Search

Ranking models have achieved promising results, but it remains challenging to design personalized ranking systems to leverage user profiles and semantic representations between queries and documents. In this paper, we propose a topic-based personalized ranking model (TPRM) that integrates user topical profile with pretrained contextualized term representations to tailor the general document ranking list. Experiments on the real-world dataset demonstrate that TPRM outperforms state-of-the-art ad-hoc ranking models and personalized ranking models significantly.

cs.IR↗

arXiv2012

New Result in the Production and Decay of an Isotope, 278[113], of the 113th Element

An isotope of the 113th element, i.e., 278[113], was produced in a nuclear reaction with a 70Zn beam on a 209Bi target. We observed six consecutive α-decays following the implantation of a heavy particle in nearly the same position in the semiconductor detector under an extremely low background condition. The fifth and sixth decays are fully consistent with the sequential decays of 262Db and 258Lr in both decay energies and decay times. This indicates that the present decay chain consisted of 278[113], 274Rg (Z=111), 270Mt (Z=109), 266Bh (Z=107), 262Db (Z=105), and 258Lr (Z=103) with firm connections. This result, together with previously reported results from 2004 and 2007, conclusively leads to the unambiguous production and identification of the isotope 278[113] of the 113th element.

nucl-ex↗