Search Results for author:
Found 24 papers, 19 papers with code
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
This iterative cycle of exploration and training fosters continued improvement in the agents.
PST-Bench: Tracing and Benchmarking the Source of Publications
Tracing the source of research papers is a fundamental yet challenging task for researchers.
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
To foster generalizable agent learning, we collect large-scale, unified, and high-quality training annotations derived from diverse ground-truth reasoning rationales across various complex interactive tasks.
Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts
Using counterfactual data augmentation to the FairytaleQA dataset, we evaluate model robustness against swapped gender character information, and then mitigate learned biases by introducing counterfactual gender stereotypes during training time.
The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
Causal reasoning, the ability to identify cause-and-effect relationship, is crucial in human thinking.
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation
Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses.
KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references.
GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods
A key goal for the advancement of AI is to develop technologies that serve the needs not just of one group but of all communities regardless of their geographical region.
How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?
To this end, we introduce an Ethical NaTural Language Interventions in Text-to-Image GENeration (ENTIGEN) benchmark dataset to evaluate the change in image generations conditional on ethical interventions across three social axes -- gender, skin color, and culture.
Cultural Vocal Bursts Intensity Prediction
Text-to-Image Generation
Towards a Unified Multi-Dimensional Evaluator for Text Generation
We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.
GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models
In this paper, we introduce a benchmark dataset, Geo-Diverse Commonsense Multilingual Language Models Analysis (GeoMLAMA), for probing the diversity of the relational knowledge in multilingual PLMs.
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
We probe PLMs and models with visual signals, including vision-language pretrained models and image synthesis models, on this benchmark, and find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models.
A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models
With the increasing of model capacity brought by pre-trained language models, there emerges boosting needs for more knowledgeable natural language processing (NLP) models with advanced functionalities including providing and making flexible use of encyclopedic and commonsense knowledge.
Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning
To bridge this gap, we present the Graph Robustness Benchmark (GRB) with the goal of providing a scalable, unified, modular, and reproducible evaluation for the adversarial robustness of GML models.
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning
Commonsense is defined as the knowledge that is shared by everyone.
Ranked #1 on
Visual Commonsense Reasoning
on GD-VCR
Cultural Vocal Bursts Intensity Prediction
Visual Commonsense Reasoning
CogView: Mastering Text-to-Image Generation via Transformers
Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding.
Ranked #56 on
Text-to-Image Generation
on MS COCO
(using extra training data)
Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Causal inference is the process of capturing cause-effect relationship among variables.
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed.
Controllable Generation from Pre-trained Language Models via Inverse Prompting
To tackle this challenge, we propose an innovative method, inverse prompting, to better control text generation.
OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services
Academic knowledge services have substantially facilitated the development of the science enterprise by providing a plenitude of efficient research tools.
What Does BERT with Vision Look At?
Pre-trained visually grounded language models such as ViLBERT, LXMERT, and UNITER have achieved significant performance improvement on vision-and-language tasks but what they learn during pre-training remains unclear.
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment semantics.
VisualBERT: A Simple and Performant Baseline for Vision and Language
We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks.
Ranked #1 on
Visual Reasoning
on NLVR
A Soft Label Strategy for Target-Level Sentiment Classification
In this paper, we propose a soft label approach to target-level sentiment classification task, in which a history-based soft labeling model is proposed to measure the possibility of a context word as an opinion word.
