Search Results for author:
Found 24 papers, 18 papers with code
Red Dragon AI at TextGraphs 2020 Shared Task : LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking
Explainable question answering for science questions is a challenging task that requires multi-hop inference over a large set of fact sentences.
PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference
To address this, we propose PromptDistill, a novel, training-free method that improves inference efficiency while preserving generation quality.
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Our results reveal that o-[n] series, particularly later iterations like o3 and o4-mini, significantly outperform the GPT-[n] series and show strong scalability in multimodal reasoning.
M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework
In this work, we introduce M-LongDoc, a benchmark of 851 samples, and an automated framework to evaluate the performance of large multimodal models.
Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
Large multimodal models have demonstrated impressive problem-solving abilities in vision and language tasks, and have the potential to encode extensive world knowledge.
SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages
Large Language Models (LLMs) have shown remarkable abilities across various tasks, yet their development has predominantly centered on high-resource languages like English and Chinese, leaving low-resource languages underserved.
Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions
During the peer battles, we observe intriguing scenarios where the LLM candidates display competitive behaviors and even learn from the opponents.
PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns
To diagnose the reasoning challenges in large multimodal models, we progressively guide the models with our ground truth reasoning explanations for visual perception, inductive reasoning, and deductive reasoning.
SeaLLMs -- Large Language Models for Southeast Asia
Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regional languages.
Contrastive Chain-of-Thought Prompting
Compared to the conventional chain of thought, our approach provides both valid and invalid reasoning demonstrations, to guide the model to reason step-by-step while reducing reasoning mistakes.
Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning
Interestingly, despite being introduced four years ago, T5-based LLMs, such as FLAN-T5, continue to outperform the latest decoder-based LLMs, such as LLAMA and VICUNA, on tasks that require general problem-solving skills.
M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models
M3Exam exhibits three unique characteristics: (1) multilingualism, encompassing questions from multiple countries that require strong multilingual proficiency and cultural knowledge; (2) multimodality, accounting for the multimodal nature of many exam questions to test the model's multimodal understanding capability; and (3) multilevel structure, featuring exams from three critical educational periods to comprehensively assess a model's proficiency at different levels.
INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models
Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents.
Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction
Through comprehensive experiments involving multiple tasks, settings, and models, we demonstrate that CASE can serve as a general decoding strategy for complex sentiment tasks.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
Specifically, CoK consists of three stages: reasoning preparation, dynamic knowledge adapting, and answer consolidation.
Is GPT-3 a Good Data Annotator?
In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks.
A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach
Hence, we propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers.
Ranked #2 on
Hyper-Relational Extraction
on HyperRED
RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction
We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods.
Ranked #1 on
Zero-shot Relation Triplet Extraction
on Wiki-ZSL
Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term.
Ranked #3 on
Aspect Sentiment Triplet Extraction
on MuseASTE
Aspect-Based Sentiment Analysis (ABSA)
Aspect Sentiment Triplet Extraction
+3
Red Dragon AI at TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking
Explainable question answering for science questions is a challenging task that requires multi-hop inference over a large set of fact sentences.
Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation
The TextGraphs-13 Shared Task on Explanation Regeneration asked participants to develop methods to reconstruct gold explanations for elementary science questions.
Scene Graph Parsing by Attention Graph
Scene graph representations, which form a graph of visual object nodes together with their attributes and relations, have proved useful across a variety of vision and language applications.
Transformer to CNN: Label-scarce distillation for efficient text classification
Significant advances have been made in Natural Language Processing (NLP) modelling since the beginning of 2018.
