Search Results for author:
Found 43 papers, 29 papers with code
Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising
In this paper, we propose a Spatial Hierarchy Aware Residual Pyramid Network, called SHARP-Net, to remove the depth noise by fully exploiting the geometry information of the scene on different scales.
Search-o1: Agentic Search-Enhanced Large Reasoning Models
To address this limitation, we introduce \textbf{Search-o1}, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents.
Ranked #1 on
Mathematical Reasoning
on MATH500
Progressive Multimodal Reasoning via Active Retrieval
To bridge the gap in automated multimodal reasoning verification, we employ the MCTS algorithm combined with an active retrieval mechanism, which enables the automatic generation of step-wise annotations.
Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models
The rapidly developing field of large multimodal models (LMMs) has led to the emergence of diverse models with remarkable capabilities.
Smaller Language Models Are Better Instruction Evolvers
In this study, we question this prevalent assumption and conduct an in-depth exploration into the potential of smaller language models (SLMs) in the context of instruction evolution.
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval.
Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
Due to its robust pipeline design, FollowRAG can seamlessly integrate with different RAG benchmarks.
MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
Long-term memory is significant for agents, in which insights play a crucial role.
How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
Based on our selected data, we present XCoder, a family of models finetuned from LLaMA3.
Qwen2 Technical Report
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models.
Ranked #2 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoning
In this paper, we introduce a series of LLMs that employs the Decomposition of thought with code assistance and self-correction for mathematical reasoning, dubbed as DotaMath.
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage.
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
Based on preference data, DPA-RAG accomplishes both external and internal preference alignment: 1) It jointly integrate pair-wise, point-wise, and contrastive preference alignment abilities into the reranker, achieving external preference alignment among RAG components.
Ranked #2 on
Knowledge Base Question Answering
on WebQuestionsSP
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
AutoIF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness.
Ranked #1 on
Instruction Following
on IFEval
CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
Computer Science (CS) stands as a testament to the intricacies of human intelligence, profoundly advancing the development of artificial intelligence and modern society.
Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
In this study, we address the challenges posed by input perturbations in slot filling by proposing Noise-BERT, a unified Perturbation-Robust Framework with Noise Alignment Pre-training.
PreAct: Prediction Enhances Agent's Planning Ability
Addressing the disparity between forecasts and actual results can enable individuals to expand their thought processes and stimulate self-reflection, thus promoting accurate planning.
Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models
In this work, we focus on improving the confidence estimation of large language models.
DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
It learns diverse instruction targets and combines a code evaluation objective to enhance its code generation ability.
Knowledge Editing on Black-box Large Language Models
Knowledge editing (KE) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowledge.
OccuQuest: Mitigating Occupational Bias for Inclusive Large Language Models
Furthermore, we assemble three test sets for comprehensive evaluation, an occu-test set covering 25 occupational categories, an estate set focusing on real estate, and an occu-quora set containing real-world questions from Quora.
Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT
The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to task-oriented dialogue (TOD) systems.
Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking
Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time-consuming and costly.
Type-aware Decoding via Explicitly Aggregating Event Information for Document-level Event Extraction
Although previous methods attempt to address these challenges, they overlook the interference of event-unrelated sentences during event detection and neglect the mutual interference of different event roles during argument extraction.
DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction
Most current Event Extraction (EE) methods focus on the high-resource scenario, which requires a large amount of annotated data and can hardly be applied to low-resource domains.
DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task
Recently, prompt-based generative frameworks have shown impressive capabilities in sequence labeling tasks.
ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models
Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing.
Ranked #1 on
Knowledge Base Question Answering
on WebQuestionsSP
Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task
To address these challenges, we propose a unified robustness evaluation framework based on the slot-filling task to systematically evaluate the dialogue understanding capability of LLMs in diverse input perturbation scenarios.
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
In this paper, we conduct an investigation for such data augmentation in math reasoning and are intended to answer: (1) What strategies of data augmentation are more effective; (2) What is the scaling relationship between the amount of augmented data and model performance; and (3) Can data augmentation incentivize generalization to out-of-domain mathematical reasoning tasks?
Ranked #59 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies.
Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
The proposed dataset contains five types of human-annotated noise, and all those noises are exactly existed in real extensive robust-training methods of slot filling into the proposed framework.
InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models
The field of emotion recognition of conversation (ERC) has been focusing on separating sentence feature encoding and context modeling, lacking exploration in generative paradigms based on unified designs.
Ranked #3 on
Emotion Recognition in Conversation
on EmoryNLP
Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
Our model achieves state-of-the-art performance on three datasets, demonstrating the superiority of our work.
A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances.
Ranked #1 on
Few-shot NER
on Few-NERD (INTER)
Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA
Knowledge Base Question Answering (KBQA) aims to answer natural language questions with factual information such as entities and relations in KBs.
Ranked #3 on
Knowledge Base Question Answering
on WebQuestionsSP
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
We find with augmented samples containing more distinct reasoning paths, RFT improves mathematical reasoning performance more for LLMs.
Ranked #108 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting
Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source domain to the unlabeled target domain.
Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
In real dialogue scenarios, the existing slot filling model, which tends to memorize entity patterns, has a significantly reduced generalization facing Out-of-Vocabulary (OOV) problems.
A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition
Specifically, we decouple class-specific prototypes and contextual semantic prototypes by two masking strategies to lead the model to focus on two different semantic information for inference.
Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals.
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling
Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data.
A Robust Contrastive Alignment Method For Multi-Domain Text Classification
In this paper, we propose a robust contrastive alignment method to align text classification features of various domains in the same feature space by supervised contrastive learning.
Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation
Previous LiDAR scene flow estimation methods, especially recurrent neural networks, usually suffer from structure distortion in challenging cases, such as sparse reflection and motion occlusions.
