Search Results for author:
Found 33 papers, 9 papers with code
Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
Existing work investigating this reasoning ability of LLMs has focused only on a couple of inference rules (such as modus ponens and modus tollens) of propositional and first-order logic.
Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation
We introduce a benchmark, LenCom-Eval, specifically designed for testing models' capability in generating images with Lengthy and Complex visual text.
Optical Character Recognition (OCR)
Text-to-Image Generation
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
Nevertheless, the frozen visual encoder in autoregressive VLMs imposes constraints on the learning of conventional image triggers.
In-context Learning with Retrieved Demonstrations for Language Models: A Survey
Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context.
Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
This work strives to understand the proficiency of LLMs in logical reasoning by offering a brief review of the latest progress in this area; with a focus on the logical reasoning datasets, tasks, and the methods adopted to utilize LLMs for reasoning.
MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation
We introduce a unified score for the ADD system that takes into account the interplay between symptoms and diagnosis.
End-to-end Knowledge Retrieval with Multi-modal Queries
We investigate knowledge retrieval with multi-modal queries, i. e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval.
Dr.ICL: Demonstration-Retrieved In-context Learning
In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs.
Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?
Can state-of-the-art NLP models correctly reason over the contexts of such scenarios?
Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?
Comparing with the FiD reader, this approach matches its accuracy by utilizing just 18. 32% of its reader inference cost and also outperforms it by achieving up to 55. 10% accuracy on NQ Open.
Fleet Rebalancing for Expanding Shared e-Mobility Systems: A Multi-agent Deep Reinforcement Learning Approach
This is particularly challenging in the context of expanding systems, because i) the range of the EVs is limited while charging time is typically long, which constrain the viable rebalancing operations; and ii) the EV stations in the system are dynamically changing, i. e., the legitimate targets for rebalancing operations can vary over time.
A Study on the Efficiency and Generalization of Light Hybrid Retrievers
Driven by this question, we leverage an indexing-efficient dense retriever (i. e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost.
Multi-Forgery Detection Challenge 2022: Push the Frontier of Unconstrained and Diverse Forgery Detection
In this paper, we present the solutions from the Top 3 teams, in order to boost the research work in the field of image forgery detection.
BioTABQA: Instruction Learning for Biomedical Table Question Answering
To the best of our knowledge, none of TQA datasets exist in the biomedical domain where tables are frequently used to present information.
Neural Retriever and Go Beyond: A Thesis Proposal
First, we introduce methods to address the abovementioned issues of neural retrievers from three angles, new model architectures, IR-oriented pretraining tasks, and generating large scale training data.
In-BoXBART: Get Instructions into Biomedical Multi-Task Learning
Recently, instructional prompts have shown significant improvement towards multi-task generalization; however, the effect of instructional prompts and Multi-Task Learning (MTL) has not been systematically studied in the biomedical domain.
Improving Contrastive Learning with Model Augmentation
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness
However, the effect of data modification on adversarial robustness remains unclear.
Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering
Among several interesting findings, it is important to highlight that (1) the generative readers perform better in long context QA, (2) the extractive readers perform better in short context while also showing better out-of-domain generalization, and (3) the encoder of encoder-decoder PrLMs (e. g., T5) turns out to be a strong extractive reader and outperforms the standard choice of encoder-only PrLMs (e. g., RoBERTa).
Improving Biomedical Information Retrieval with Neural Retrievers
We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.
Deployment Optimization for Shared e-Mobility Systems with Multi-agent Deep Neural Search
Shared e-mobility services have been widely tested and piloted in cities across the globe, and already woven into the fabric of modern urban planning.
Self-supervised Learning for Sequential Recommendation with Model Augmentation
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Context
Furthermore, we propose consistency and similarity constraints to promote the correlation and interaction between passage ranking and sentence selection. The experiments demonstrate that our framework can achieve competitive results with previous systems and outperform the baseline by 28\% in terms of exact matching of relevant sentences on the HotpotQA dataset.
Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering
The visual retriever aims to retrieve relevant knowledge, and the visual reader seeks to predict answers based on given knowledge.
Deep Signature FBSDE Algorithm
We propose a deep signature/log-signature FBSDE algorithm to solve forward-backward stochastic differential equations (FBSDEs) with state and path dependent features.
`Just because you are right, doesn't mean I am wrong': Overcoming a bottleneck in development and evaluation of Open-Ended VQA tasks
GQA (CITATION) is a dataset for real-world visual reasoning and compositional question answering.
'Just because you are right, doesn't mean I am wrong': Overcoming a Bottleneck in the Development and Evaluation of Open-Ended Visual Question Answering (VQA) Tasks
GQA~\citep{hudson2019gqa} is a dataset for real-world visual reasoning and compositional question answering.
CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
It is the largest face anti-spoofing dataset in terms of the numbers of the data and the subjects.
Unitary Approximate Message Passing for Sparse Bayesian Learning
Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm.
Can Transformers Reason About Effects of Actions?
A recent work has shown that transformers are able to "reason" with facts and rules in a limited setting where the rules are natural language expressions of conjunctions of conditions implying a conclusion.
Strong Equivalence for LPMLN Programs
We show that the verification of strong equivalence in LPMLN can be reduced to equivalence checking in classical logic via a reduct and choice rules as well as to equivalence checking under the "soft" logic of here-and-there.
Strong equivalence for $\rm LP^{MLN}$ programs
Strong equivalence is a well-studied and important concept in answer set programming (ASP).
Logic in Computer Science
Demand Prediction for Electric Vehicle Sharing
Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe.
