Search Results for author:
Found 29 papers, 10 papers with code
DCU-Lorcan at FinCausal 2022: Span-based Causality Extraction from Financial Documents using Pre-trained Language Models
In this paper, we describe our DCU-Lorcan system for the FinCausal 2022 shared task: span-based cause and effect extraction from financial documents.
Findings of the WMT 2024 Shared Task on Discourse-Level Literary Translation
Following last year, we have continued to host the WMT translation shared task this year, the second edition of the Discourse-Level Literary Translation.
Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement
We have collected a substantial amount of multilingual data for several low-resource languages and conducted extensive continual pre-training using the Qwen2 models.
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
Currently OpenAI o1 sparks a surge of interest in the study of large reasoning models (LRM).
Large Language Models as Code Executors: An Exploratory Study
The capabilities of Large Language Models (LLMs) have significantly evolved, extending from natural language processing to complex tasks like code understanding and generation.
Reference-free Hallucination Detection for Large Vision-Language Models
In particular, we conduct an extensive study on three kinds of techniques: uncertainty-based, consistency-based, and supervised uncertainty quantification methods on four representative LVLMs across two different tasks.
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data.
Can a Multichoice Dataset be Repurposed for Extractive Question Answering?
The rapid evolution of Natural Language Processing (NLP) has favored major languages such as English, leaving a significant gap for many others due to limited resources.
Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, fundamentally reshaping the landscape of natural language processing (NLP) research.
Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models
The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks.
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation.
A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering
The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA).
Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs
To foster progress in this domain, we hold a new shared task at WMT 2023, the first edition of the Discourse-Level Literary Translation.
On the Cultural Gap in Text-to-Image Generation
Accordingly, we propose a novel multi-modal metric that considers object-text alignment to filter the fine-tuning data in the target culture, which is used to fine-tune a T2I model to improve cross-cultural generation.
Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration
Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text has not been fully studied.
Out-of-Distribution Generalization in Text Classification: Past, Present, and Future
Machine learning (ML) systems in natural language processing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differs from the training data distribution.
Is a Video worth $n\times n$ Images? A Highly Efficient Approach to Transformer-based Video Question Answering
We show that by integrating our approach into VideoQA systems we can achieve comparable, even superior, performance with a significant speed up for training and inference.
Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering
Specifically, we explicitly use the Semantic Role Labeling (SRL) structure of the question in the dynamic reasoning process where we decide to move to the next frame based on which part of the SRL structure (agent, verb, patient, etc.)
A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models
We conclude by emphasizing the critical role of LLMs in guiding the future evolution of MT and offer a roadmap for future exploration in the sector.
Document-Level Machine Translation with Large Language Models
Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing (NLP) tasks.
Dialogue-to-Video Retrieval
Recent years have witnessed an increasing amount of dialogue/conversation on the web especially on social media.
Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis
User and product information associated with a review is useful for sentiment polarity prediction.
QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Question Generation (QG) aims to automate the task of composing questions for a passage with a set of chosen answers found within the passage.
Extending the Scope of Out-of-Domain: Examining QA models in multiple subdomains
Past works that investigate out-of-domain performance of QA systems have mainly focused on general domains (e. g. news domain, wikipedia domain), underestimating the importance of subdomains defined by the internal characteristics of QA datasets.
Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Answering the distress call of competitions that have emphasized the urgent need for better evaluation techniques in dialogue, we present the successful development of human evaluation that is highly reliable while still remaining feasible and low cost.
Improving Unsupervised Question Answering via Summarization-Informed Question Generation
Template-based QG uses linguistically-informed heuristics to transform declarative sentences into interrogatives, whereas supervised QG uses existing Question Answering (QA) datasets to train a system to generate a question given a passage and an answer.
Improving Document-Level Sentiment Analysis with User and Product Context
We achieve this by explicitly storing representations of reviews written by the same user and about the same product and force the model to memorize all reviews for one particular user and product.
UNIFUZZ: A Holistic and Pragmatic Metrics-Driven Platform for Evaluating Fuzzers
We hope that our findings can shed light on reliable fuzzing evaluation, so that we can discover promising fuzzing primitives to effectively facilitate fuzzer designs in the future.
Cryptography and Security
SmartSeed: Smart Seed Generation for Efficient Fuzzing
In total, our system discovers more than twice unique crashes and 5, 040 extra unique paths than the existing best seed selection strategy for the evaluated 12 applications.
Cryptography and Security
