Search Results for author:
Found 70 papers, 30 papers with code
Personal Information Leakage Detection in Conversations
In this work, we propose to protect personal information by warning users of detected suspicious sentences generated by conversational assistants.
RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment.
Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
However, the contrastive method ignores the temporal information when measuring similarity across acoustic and linguistic modalities, leading to inferior performance.
Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
Our results under these settings demonstrate that open-source audio LMMs suffer an average attack success rate of 69. 14% on harmful audio questions, and exhibit safety vulnerabilities when distracted with non-speech audio noise.
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
In this paper, we introduce GraphFilter, a novel method that represents the dataset as a bipartite graph, linking sentences to their constituent n-grams.
Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
Moreover, JSP achieves a state-of-the-art attack success rate of 92% on GPT-4 on the harmful query benchmark, and exhibits strong resistant to defence strategies.
Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues
Our empirical results show: (i) the quality of the SCNs derived from synthetic data is comparable to that from real dialogues annotated with gold frames, and (ii) the quality of the SCNs extracted from real data, annotated with either silver (predicted) or gold frames, surpasses that without the frame annotations.
NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions
This paper addresses the problem of autonomous UAV search missions, where a UAV must locate specific Entities of Interest (EOIs) within a time limit, based on brief descriptions in large, hazard-prone environments with keep-out zones.
Learning in Order! A Sequential Strategy to Learn Invariant Features for Multimodal Sentiment Analysis
This work proposes a novel and simple sequential learning strategy to train models on videos and texts for multimodal sentiment analysis.
From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Recent advances in artificial intelligence have seen Large Language Models (LLMs) demonstrate notable proficiency in causal discovery tasks.
Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights
Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk.
CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems
Automatically evaluating the quality of responses in open-domain dialogue systems is a challenging but crucial task.
Bridging Law and Data: Augmenting Reasoning via a Semi-Structured Dataset with IRAC methodology
This paper introduces LEGALSEMI, a benchmark specifically curated for legal scenario analysis.
Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction
Inspired by causal discovery, we propose a novel deep latent model in the variational autoencoder (VAE) framework, which not only captures the underlying latent structures of data but also utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different domains.
SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of training examples needed.
Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models
In this work, we propose a general, model-agnostic, reinforcement learning framework, Mixture-of-Skills (MoS), that learns to optimize data usage automatically during the fine-tuning process.
NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Increasing concerns about privacy leakage issues in academia and industry arise when employing NLP models from third-party providers to process sensitive texts.
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
The Learning-to-match (LTM) framework proves to be an effective inverse optimal transport approach for learning the underlying ground metric between two sources of data, facilitating subsequent matching.
What Can Natural Language Processing Do for Peer Review?
We hope that our work will help set the agenda for research in machine-assisted scientific quality control in the age of AI, within the NLP community and beyond.
IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models
Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains.
Generative Region-Language Pretraining for Open-Ended Object Detection
To address it, we formulate object detection as a generative problem and propose a simple framework named GenerateU, which can detect dense objects and generate their names in a free-form way.
FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning
Federated instruction tuning (FedIT) has emerged as a promising solution, by consolidating collaborative training across multiple data owners, thereby resulting in a privacy-preserving learning model.
RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations
While collecting sufficient human-authored data is costly, synthetic conversations provide suitable amounts of data to help mitigate the scarcity of training data, as well as the chance to assess the alignment between LLMs and humans in the awareness of social norms.
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Negotiation is a crucial ability in human communication.
Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues
We introduce a simple tuning-free and label-free In-Context Learning (ICL) method to identify high-quality ICL exemplars for the remediator, where we propose a novel select criteria, called value impact, to measure the quality of the negotiation outcomes.
SADAS: A Dialogue Assistant System Towards Remediating Norm Violations in Bilingual Socio-Cultural Conversations
We have released our code and software at:~\url{https://github. com/AnonymousEACLDemo/SADAS}.
Importance-Aware Data Augmentation for Document-Level Neural Machine Translation
Document-level neural machine translation (DocNMT) aims to generate translations that are both coherent and cohesive, in contrast to its sentence-level counterpart.
Adapting Large Language Models for Document-Level Machine Translation
We provide an in-depth analysis of these LLMs tailored for DocMT, examining translation errors, discourse phenomena, strategies for training and inference, the data efficiency of parallel documents, recent test set evaluations, and zero-shot crosslingual transfer.
TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce
Annually, e-commerce platforms incur substantial financial losses due to trademark infringements, making it crucial to identify and mitigate potential legal risks tied to merchant information registered to the platforms.
Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?
Each scenario in the corpus is annotated with a complete IRAC analysis in a semi-structured format so that both machines and legal professionals are able to interpret and understand the annotations.
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval.
Ranked #2 on
Human Judgment Correlation
on Flickr8k-Expert
The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning
Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem.
Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding
Our model parses a form into a word-relation graph in order to identify entities and relations jointly and reduce the time complexity of inference.
Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation
Flowchart-grounded troubleshooting dialogue (FTD) systems, which follow the instructions of a flowchart to diagnose users' problems in specific domains (e. g., vehicle, laptop), have been gaining research interest in recent years.
SocialDial: A Benchmark for Socially-Aware Dialogue Systems
To the best of our knowledge, SocialDial is the first socially-aware dialogue dataset that covers multiple social factors and has fine-grained labels.
Cultural Vocal Bursts Intensity Prediction
Synthetic Data Generation
Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery
In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work.
Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation
Existing work in document-level neural machine translation commonly concatenates several consecutive sentences as a pseudo-document, and then learns inter-sentential dependencies.
When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods
To facilitate the research of PETuning in FL, we also develop a federated tuning framework FedPETuning, which allows practitioners to exploit different PETuning methods under the FL training paradigm conveniently.
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Negotiation is one of the crucial abilities in human communication, and there has been a resurgent research interest in negotiation dialogue systems recently, which goal is to empower intelligent agents with such ability that can efficiently help humans resolve conflicts or reach beneficial agreements.
Learning Object-Language Alignments for Open-Vocabulary Object Detection
In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data.
ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities
We introduce ViLPAct, a novel vision-language benchmark for human activity planning.
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation
In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples.
Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions with the environment during moving.
Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model
The ability to generate natural-language questions with controlled complexity levels is highly desirable as it further expands the applicability of question generation.
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers
We conduct extensive experiments to study the research problems involved in continual semantic parsing and demonstrate that a neural semantic parser trained with TotalRecall achieves superior performance than the one trained directly with the SOTA continual learning algorithms and achieve a 3-6 times speedup compared to re-training from scratch.
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
Machine-learning-as-a-service (MLaaS) has attracted millions of users to their splendid large-scale models.
Neural-Symbolic Commonsense Reasoner with Relation Predictors
The dynamic nature of commonsense knowledge postulates models capable of performing multi-hop reasoning over new situations.
On Robustness of Neural Semantic Parsers
In this paper, we provide the empirical study on the robustness of semantic parsers in the presence of adversarial attacks.
Few-Shot Semantic Parsing for New Predicates
In this work, we investigate the problems of semantic parsing in a few-shot learning setting.
COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering
However, current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation, mostly due to incapability of identifying a diverse range of implicit social relations.
Context Dependent Semantic Parsing: A Survey
Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations.
Privacy-Aware Text Rewriting
Biased decisions made by automatic systems have led to growing concerns in research communities.
ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation
In this paper, we describe ALTER, an auxiliary text rewriting tool that facilitates the rewriting process for natural language generation tasks, such as paraphrasing, text simplification, fairness-aware text rewriting, and text style transfer.
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection
Due to the sharp increase in the severity of the threat imposed by software vulnerabilities, the detection of vulnerabilities in binary code has become an important concern in the software industry, such as the embedded systems industry, and in the field of computer security.
D-PAGE: Diverse Paraphrase Generation
In this paper, we investigate the diversity aspect of paraphrase generation.
f-GANs in an Information Geometric Nutshell
In this paper, we unveil a broad class of distributions for which such convergence happens --- namely, deformed exponential families, a wide superset of exponential families --- and show tight connections with the three other key GAN parameters: loss, game and architecture.
Demographic Inference on Twitter using Recursive Neural Networks
In social media, demographic inference is a critical task in order to gain a better understanding of a cohort and to facilitate interacting with one{'}s audience.
Collective Vertex Classification Using Recursive Neural Network
In this paper, we propose a graph-based recursive neural network framework for collective vertex classification.
Automatic Generation of Grounded Visual Questions
In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image.
Named Entity Recognition for Novel Types by Transfer Learning
In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly.
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise.
Ranked #2 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
STransE: a novel embedding model of entities and relationships in knowledge bases
Knowledge bases of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks.
Neighborhood Mixture Model for Knowledge Base Completion
Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete.
Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks
Word embeddings -- distributed word representations that can be learned from unlabelled data -- have been shown to have high utility in many natural language processing applications.
Estimating Maximally Probable Constrained Relations by Mathematical Programming
Estimating (learning) a maximally probable measure, given (a training set of) related and unrelated pairs, is a convex optimization problem.
