Papers with text alignment

5 papers
SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition (2025.emnlp-main)

Copied to clipboard

Challenge: SensorLLM is a timeseries classification framework that can perform human activity recognition tasks.
Approach: They propose a framework that enables Large Language Models to perform human activity recognition from sensor time-series data.
Outcome: The proposed framework can perform human activity recognition (HAR) tasks with human inputs.
Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers (2025.findings-emnlp)

Copied to clipboard

Challenge: predicting the final label alone is insufficient and offers limited interpretability.
Approach: They propose to reframe table–text alignment as an explanation task requiring models to identify the table cells essential for claim verification.
Outcome: The proposed taxonomy improves claim verification performance and most LLMs fail to recover human-aligned rationales, suggesting that their predictions do not stem from faithful reasoning.
DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding (2026.eacl-long)

Copied to clipboard

Challenge: a benchmark of 1,272 samples containing about 1,475 unique words is available for Arabic calligraphy . the dataset reflects real-world challenges in Arabic writing, such as calligraphic variation and artistic distortions .
Approach: They evaluated 13 leading Arabic and multilingual multimodal models and paired them with sentence-level annotations to evaluate their calligraphy models.
Outcome: The benchmark evaluates 13 leading Arabic and multilingual multimodal models . it shows they struggle with calligraphic variation, artistic distortions, and precise visual–text alignment.
Universal Prompt Optimizer for Safe Text-to-Image Generation (2024.naacl-long)

Copied to clipboard

Challenge: Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications.
Approach: They propose a novel reward function measuring toxicity and text alignment of generated images and train the optimizer through Proximal Policy Optimization.
Outcome: The proposed model reduces the likelihood of various models in generating inappropriate images, with no significant impact on text alignment.
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes (2025.acl-long)

Copied to clipboard

Challenge: Text-to-image (T2I) generation models have great results in image quality, flexibility, and text alignment, but they suffer from substantial gender bias.
Approach: They propose a benchmark to study gender bias in multilingual T2I models . they use multilingual prompts to account for grammatical differences influencing gender .
Outcome: The proposed benchmark shows strong gender biases and language-specific differences across models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations