AIConfPaper
← Search

Amith Ananthram

8 accepted papers

2026

PoSh: Using Scene Graphs to Guide LLMs-as-a-Judge for Detailed Image Descriptions

Amith Ananthram, Elias Stengel-Eskin, Lorena A. Bradford, Julia Demarest, Adam Purvis, Keith Krut +4
ICLR 2026poster

While vision-language models (VLMs) have advanced into detailed image description, evaluation remains a challenge. Standard metrics (e.g. CIDEr, SPICE) were designed for short texts and tuned to recognize errors that are now uncommon, such as object misidentification. In contrast, long texts require…

Cited by 0Source ↗code ↗Scholar ↗
2025

Data Caricatures: On the Representation of African American Language in Pretraining Corpora

Nicholas Deas, Blake Vente, Amith Ananthram, Jessica A Grieser, Desmond U. Patton, Shana Kleiner +2
ACL 2025long

With a combination of quantitative experiments, human judgments, and qualitative analyses, we evaluate the quantity and quality of African American Language (AAL) representation in 12 predominantly English, open-source pretraining corpora. We specifically focus on the sources, variation, and natural…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Enhancing Multimodal Affective Analysis with Learned Live Comment Features

Zhaoyuan Deng, Amith Ananthram, Kathleen McKeown
AAAI 2025technical

Live comments, also known as Danmaku, are user-generated messages that are synchronized with video content. These comments overlay directly onto streaming videos, capturing viewer emotions and reactions in real-time. While prior work has leveraged live comments in affective analysis, its use has bee…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

Amith Ananthram, Elias Stengel-Eskin, Mohit Bansal, Kathleen McKeown
ICLR 2025poster

Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image while individuals from East Asian cultures attend more to sce…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Social Orientation: A New Feature for Dialogue Analysis

Todd Morrill, Zhaoyuan Deng, Yanda Chen, Amith Ananthram, Colin Wayne Leach, Kathleen McKeown
COLING 2024main

There are many settings where it is useful to predict and explain the success or failure of a dialogue. Circumplex theory from psychology models the social orientations (e.g., Warm-Agreeable, Arrogant-Calculating) of conversation participants and can be used to predict and explain the outcome of soc…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence

Gengyu Wang, Kate Harwood, Lawrence Chillrud, Amith Ananthram, Melanie Subbiah, Kathleen McKeown
ACL 2023findings

We present a new fact-checking benchmark, Check-COVID, that requires systems to verify claims about COVID-19 from news using evidence from scientific articles. This approach to fact-checking is particularly challenging as it requires checking internet text written in everyday language against eviden…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2022

Seeded Hierarchical Clustering for Expert-Crafted Taxonomies

Anish Saha, Amith Ananthram, Emily Allaway, Heng Ji, Kathleen McKeown
EMNLP 2022finding

Practitioners from many disciplines (e.g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora. In this work, we study Seeded Hierarchical Clustering (SHC): the task of automatically fitting unlabeled data to such taxonomies using a small set of labeled example…

Cited by 1Source ↗PDF ↗Scholar ↗
2020

Event-Guided Denoising for Multilingual Relation Learning

Amith Ananthram, Emily Allaway, Kathleen McKeown
COLING 2020main

General purpose relation extraction has recently seen considerable gains in part due to a massively data-intensive distant supervision technique from Soares et al. (2019) that produces state-of-the-art results across many benchmarks. In this work, we present a methodology for collecting high quality…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗