Search Results for author:
Found 38 papers, 21 papers with code
Mechanisms of non-factual hallucinations in language models
Our study investigates the mechanistic causes of hallucination, specifically non-factual ones where the LM incorrectly predicts object attributes in response to subject-relation queries.
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
GPT4V, the best-performing VLM, achieves 62. 99% accuracy (4-shot) on the comprehension task and 49. 7% on the localization task (4-shot and Chain-of-Thought).
Ranked #1 on
Object Localization
on IllusionVQA
DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with detailed lighting information in the form of radiance hints, i. e., visualizations of the scene geometry with a homogeneous canonical material under the target lighting.
EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models
We study how to maximize the re-ranking performance given a budget, by navigating the vast search spaces of prompt choices, LLM APIs, and budget splits.
PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering
Existing work on Temporal Question Answering (TQA) has predominantly focused on questions anchored to specific timestamps or events (e. g. "Who was the US president in 1970?").
Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision.
Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks.
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration?
Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset
Using novel approaches to dataset development, the Biasly dataset captures the nuance and subtlety of misogyny in ways that are unique within the literature.
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows.
Relighting Neural Radiance Fields with Shadow and Highlight Hints
This paper presents a novel neural implicit radiance representation for free viewpoint relighting from a small set of unstructured photographs of an object lit by a moving point light source different from the view position.
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
Specifically, we develop cross-modality attacks on alignment where we pair adversarial images going through the vision encoder with textual prompts to break the alignment of the language model.
Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection.
Learning with Rejection for Abstractive Text Summarization
State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset.
Inverse Reinforcement Learning for Text Summarization
We introduce inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models, imitating human summarization behaviors.
Text Generation with Text-Editing Models
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer.
Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization
In this work, we show that these entities are not aberrations, but they instead require utilizing external world knowledge to infer reasoning paths from entities in the source.
Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization
State-of-the-art abstractive summarization systems often generate \emph{hallucinations}; i. e., content that is not directly inferable from the source text.
Abstractive Text Summarization
Reinforcement Learning (RL)
+1
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Faceted summarization provides briefings of a document from different perspectives.
Ranked #1 on
Unsupervised Extractive Summarization
on FacetSum
Discourse-Aware Unsupervised Summarization for Long Scientific Documents
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents.
Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations.
Ranked #3 on
Image Inpainting
on FFHQ 512 x 512
On-the-Fly Attention Modulation for Neural Generation
Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense.
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles
Multi-document summarization is a challenging task for which there exists little large-scale datasets.
Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task Learning
In this paper, we report a large-scale end-to-end language-independent multilingual model for joint automatic speech recognition (ASR) and language identification (LID).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Factual Error Correction for Abstractive Summarization Models
Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset.
Multi-Fact Correction in Abstractive Text Summarization
Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE.
Object-based Illumination Estimation with Rendering-aware Neural Networks
With the estimated lighting, virtual objects can be rendered in AR scenarios with shading that is consistent to the real scene, leading to improved realism.
Discourse-Aware Unsupervised Summarization of Long Scientific Documents
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents.
Ranked #1 on
Unsupervised Extractive Summarization
on Pubmed
MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision.
Ranked #2 on
Optical Flow Estimation
on KITTI 2012
Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article.
Recursive Cascaded Networks for Unsupervised Medical Image Registration
We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration.
EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach.
Ranked #2 on
Text Simplification
on PWKP / WikiSmall
(SARI metric)
Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks
Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes.
Multi-task Learning over Graph Structures
We present two architectures for multi-task learning with neural sequence models.
A Hierarchical Neural Attention-based Text Classifier
Deep neural networks have been displaying superior performance over traditional supervised classifiers in text classification.
BanditSum: Extractive Summarization as a Contextual Bandit
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.
Ranked #10 on
Extractive Text Summarization
on CNN / Daily Mail
A Survey on Neural Network-Based Summarization Methods
Automatic text summarization, the automated process of shortening a text while reserving the main ideas of the document(s), is a critical research area in natural language processing.
Learning Non-Lambertian Object Intrinsics across ShapeNet Categories
Rendered with realistic environment maps, millions of synthetic images of objects and their corresponding albedo, shading, and specular ground-truth images are used to train an encoder-decoder CNN.
