Search Results for author:
Found 19 papers, 10 papers with code
Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems
Building on this, we introduce Magic Mushroom, a benchmark for replicating "magic mushroom" noise: contexts that appear relevant on the surface but covertly mislead RAG systems.
Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities
We systematically survey state-of-the-art advances in synthesizing LLMs and KGs for QA and compare and analyze these approaches in terms of strength, limitations, and KG requirements.
Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge
Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unified way.
Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs
For specific industrial scenarios, our framework can facilitate the training of specialized agents using domain-specific knowledge graphs for error detection, which highlights the potential industrial application value of our framework.
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
Alongside our method, we establish MMUBench, a new benchmark for MU in MLLMs and introduce a collection of metrics for its evaluation.
HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding
Table understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures. To address these challenges, we propose HGT, a framework with a heterogeneous graph (HG)-enhanced large language model (LLM) to tackle few-shot TU tasks. It leverages the LLM by aligning the table semantics with the LLM's parametric knowledge through soft prompts and instruction turning and deals with complex tables by a multi-task pre-training scheme involving three novel multi-granularity self-supervised HG pre-training objectives. We empirically demonstrate the effectiveness of HGT, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks.
MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation
Experimental results show that our framework outperforms existing open-ended text evaluation methods and achieves the highest correlation with human evaluation, which confirms the effectiveness and advancement of our framework in addressing the uncertainties and instabilities in evaluating LLMs-generated text.
DEE: Dual-stage Explainable Evaluation Method for Text Generation
Automatic methods for evaluating machine-generated texts hold significant importance due to the expanding applications of generative systems.
Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data
Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus.
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing
Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs).
Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning
Firstly we retrieve the relevant embedding from the knowledge graph by utilizing group relations in metadata and then integrate it with other modalities.
DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping
In particular, compared to the best-performing baseline, the LLM trained using our generated dataset exhibits a 10\% relative improvement in performance on AlpacaEval, despite utilizing only 1/5 of its training data.
Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family
ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge.
Ranked #1 on
Question Answering
on WebQuestionsSP
Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams
The first solution Vanilla is to perform self-training, augmenting the supervised training data with predicted pseudo-labeled instances of the current task, while replacing the full volume retraining with episodic memory replay to balance the training efficiency with the performance of previous tasks.
Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and Supervised Learning
A reinforcement learning (RL)-based DNN compression approach is used to generate the lightweight model suitable for the edge from the heavyweight model.
Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs
The high-level decoding generates an AQG as a constraint to prune the search space and reduce the locally ambiguous query graph.
Ranked #1 on
Knowledge Base Question Answering
on LC-QuAD 1.0
Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning
Compared to the larger pre-trained model and the tabular-specific pre-trained model, our approach is still competitive.
Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base
However, this candidate generation strategy ignores the structure of queries, resulting in a considerable number of noisy queries.
Ranked #2 on
Knowledge Base Question Answering
on LC-QuAD 1.0
Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator
To address this challenge, we propose a small-big model framework that deploys a big model in the cloud and a small model on the edge devices.
