Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks187 from public data
- API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs717
API-Bank is introduced, a groundbreaking benchmark, specifically designed for tool-augmented LLMs, and a runnable evaluation system consisting of 73 API tools is developed to assess the existing LLMs' capabilities in planning, retrieving, and calling APIs.
- Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning288
This work exploits large language models (LLMs) as decomposers for effective table-based reasoning, and proposes a novel ''parsing-execution-filling'' strategy to decompose a complex question into simper step-by-step sub-questions by generating intermediate SQL queries as a bridge.
- 251
- GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection187
GALAXY is a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised learning and has a stronger few-shot ability than existing models under various low-resource settings.
- A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions110
A comprehensive review on deep learning approaches for text-to-SQL parsing, including a systematical overview of pre-trained language models and existing methods, is presented.
- 95
- On the Role of Attention Heads in Large Language Model Safety87
This paper proposes a novel metric which tailored for multi-head attention, the Safety Head ImPortant Score (Ships), to assess the individual heads' contributions to model safety and introduces the Safety Attention Head AttRibution Algorithm (Sahara) to attribute the critical safety attention heads inside the model.
- 71
- Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation69
SPACE is proposed, a novel unified pre-trained dialog model learning from large-scale dialog corpora with limited annotations, which can be effectively fine-tuned on a wide range of downstream dialog tasks.
- Multiplex PCR-based next generation sequencing as a novel, targeted and accurate molecular approach for periprosthetic joint infection diagnosis59
Periprosthetic joint infection diagnosis remains challenging, and the identification of the causative microorganism is, by far, the most important aspect, so multiple PCR-based targeted next-generation sequencing (tNGS) is used to detect pathogens and provide drug resistance information.
- One-Shot Learning as Instruction Data Prospector for Large Language Models56
It is shown that instruction tuning with the top 1\% of examples curated by \textsc{Nuggets} substantially outperforms conventional methods employing the entire dataset.
- Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing56
A novel framework to elicit relational structures from large-scale pre-trained language models (PLMs) via a probing procedure based on Poincaré distance metric, and use the induced relations to augment current graph-based parsers for better schema linking is proposed.
- Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing52
This paper presents a dynamic graph framework that is capable of effectively modelling contextual utterances, tokens, database schemas, and their complicated interaction as the conversation proceeds, and employs a dynamic memory decay mechanism that incorporates inductive bias to integrate enriched contextual relation representation.
- MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct49
This work proposes MMEvol, a novel multimodal instruction data evolution framework that iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities.
- Analysis of factors influencing the outpatient workload at Chinese health centres46
Several key factors are suggested for increasing the outpatient workload (OW) at the HCs: establishing an adequate referral system among the different levels of the health system; enhancing the qualification of health personnel and increasing the compensation by the health insurance for services provided at HCs.
- Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems44
The concept of full-duplex in telecommunication is used to demonstrate what a human-like interactive experience should be and how to achieve smooth turn-taking through three subtasks: user state detection, backchannel selection, and barge-in detection.
- 43
- UniSA: Unified Generative Framework for Sentiment Analysis40
This work proposes a Task-Specific Prompt method to jointly model subtasks and introduces a multimodal generative framework called UniSA, and designs novel pre-training tasks and training methods to enable the model to learn generic sentiment knowledge among subtasks to improve the model's multi-modal sentiment perception ability.
- 37
- 30
- 27
- 27
- 26
- 23
- 21
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.