Search Results for author:
Found 35 papers, 24 papers with code
Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach
In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models.
Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
In this paper, we present T1 to scale RL by encouraging exploration and understand inference scaling.
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
This paper introduces LongBench v2, a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks.
LongReward: Improving Long-context Large Language Models with AI Feedback
Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT models and leads to inherent limitations.
Pre-training Distillation for Large Language Models: A Design Space Exploration
Previous work applying KD in the field of large language models (LLMs) typically focused on the post-training phase, where the student LLM learns directly from instructions and corresponding responses generated by the teacher model.
Active-Passive Federated Learning for Vertically Partitioned Multi-view Data
Vertical federated learning is a natural and elegant approach to integrate multi-view data vertically partitioned across devices (clients) while preserving their privacies.
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
Though current long-context large language models (LLMs) have demonstrated impressive capacities in answering user questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to concerns about their trustworthiness due to their potential hallucinations.
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10, 000 words while maintaining output quality.
SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency.
Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models
However, knowledge in the document may conflict with the memory of LLMs due to outdated or incorrect knowledge in the LLMs' parameters.
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length.
Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions
During reasoning, for leaf nodes, LLMs choose a more confident answer from Closed-book QA that employs parametric knowledge and Open-book QA that employs retrieved external knowledge, thus eliminating the negative retrieval problem.
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding.
KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
However, these benchmarks have encountered two major limitations.
VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering
We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries.
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
To facilitate reasoning, we propose a novel two-stage XQA framework, Reasoning over Hierarchical Question Decomposition Tree (RoHT).
Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization
QTO finds the optimal solution by a forward-backward propagation on the tree-like computation graph, i. e., query computation tree.
Ranked #1 on
Complex Query Answering
on NELL-995
Reconfigurable Intelligent Surfaces for 6G -- Applications, Challenges and Solutions
It is expected that scholars will continuously strengthen the depth and breadth of theoretical research on RIS, and provide a higher theoretical upper bound for the engineering application of RIS.
Step out of KG: Knowledge Graph Completion via Knowledgeable Retrieval and Reading Comprehension
To alleviate this problem, we propose a new model based on information retrieval and reading comprehension, namely IR4KGC.
Network Coexistence Analysis of RIS-Assisted Wireless Communications
Reconfigurable intelligent surfaces (RISs) have attracted the attention of academia and industry circles because of their ability to control the electromagnetic characteristics of channel environments.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Interactive Contrastive Learning for Self-supervised Entity Alignment
Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments.
Program Transfer for Answering Complex Questions over Knowledge Bases
In this paper, we propose the approach of program transfer, which aims to leverage the valuable program annotations on the rich-resourced KBs as external supervision signals to aid program induction for the low-resourced KBs that lack program annotations.
Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making
Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts.
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability
However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them.
Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
On the one hand, sparse KGs contain less information, which makes it difficult for the model to choose correct paths.
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
Based on the datasets, we propose novel tasks such as multi-hop knowledge abstraction (MKA), multi-hop knowledge concretization (MKC) and then design a comprehensive benchmark.
Music Style Classification with Compared Methods in XGB and BPNN
Scientists have used many different classification methods to solve the problem of music classification.
Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
Multi-hop knowledge graph (KG) reasoning is an effective and explainable method for predicting the target entity via reasoning paths in query answering (QA) task.
Ranked #3 on
Link Prediction
on NELL-995
Differentiating Concepts and Instances for Knowledge Graph Embedding
Most conventional knowledge embedding methods encode both entities (concepts and instances) and relations as vectors in a low dimensional semantic space equally, ignoring the difference between concepts and instances.
Ranked #1 on
Link Prediction
on YAGO39K
OpenKE: An Open Toolkit for Knowledge Embedding
We release an open toolkit for knowledge embedding (OpenKE), which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space.
