activity
20162024
most citedA Survey on Programmatic Weak Supervision

40 citations · 101 across the 14 of their papers we have counts for

collaborators
Showing 2024Show all

6 papers · 1 filter

cs.CL2024

The Hard Positive Truth about Vision-Language Compositionality

Amita Kamath, Cheng-Yu Hsieh, Kai-Wei Chang +1

Several benchmarks have concluded that our best vision-language models (e.g., CLIP) are lacking in compositionality. Given an image, these benchmarks probe a model's ability to ide…

cs.CL2024

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li +8

Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phe…

cs.CL2024★ 3 cited

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh +3

When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccur…

cs.CV2024

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

Yu-Guan Hsieh, Cheng-Yu Hsieh, Shih-Ying Yeh +7

Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop mode…

cs.LG2024★ 7 cited

DataComp-LM: In search of the next generation of training sets for language models

Jeffrey Li, Alex Fang, Georgios Smyrnis +56

We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…

cs.CV2024

The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better

Scott Geng, Cheng-Yu Hsieh, Vivek Ramanujan +4

Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic dat…