Papers by David Ross
Improving Model Evaluation using SMART Filtering of Benchmark Datasets (2025.naacl-long)
Copied to clipboard
| Challenge: | Creating high quality human-annotated datasets is difficult due to dataset saturation. |
| Approach: | They propose a method to filter a subset of test examples from existing benchmarks by removing less informative and lower quality examples. |
| Outcome: | The proposed method reduces dataset size by 48% while increasing Pearson correlation with rankings from ChatBot Arena. |
Distribution Aware Metrics for Conditional Natural Language Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing metrics for conditional natural language generation rely on pairwise comparisons between a single generated text and the best-matching reference. |
| Approach: | They propose a family of meta-metrics that build on existing pairwise distance functions to evaluate conditional natural language generation models. |
| Outcome: | The proposed method evaluates the ability of a model to generate text matching diversity in references in visual description and summarization. |
Scaling Collaborative Effort with Agents (2026.findings-acl)
Copied to clipboard
Shannon Zejiang Shen, Valerie Chen, Ken Gu, Alexis Ross, Zixian Ma, Jillian Ross, Alex Gu, Chenglei Si, Wayne Chi, Andi Peng, Jocelyn J Shen, Ameet Talwalkar, Tongshuang Wu, David Sontag
| Challenge: | Current evaluations of agents focus on producing high-quality, final outputs in one shot, failing to account for the inherently iterative nature of many real-world problems. |
| Approach: | They propose a framework that captures how an agent’s utility grows with increasing user involvement. |
| Outcome: | The proposed framework captures how an agent’s utility grows with increasing user involvement, revealing a missing ingredient in agent design: the ability to sustain engagement and scaffold user understanding. |
IC3: Image Captioning by Committee Consensus (2023.emnlp-main)
Copied to clipboard
| Challenge: | Traditionally, image captioning models are trained to generate a single “best’ (most like a reference) image caption. |
| Approach: | They propose a method to generate a single caption that captures high-level details from several annotator viewpoints. |
| Outcome: | The proposed method outperforms baseline SOTA models and improves the performance of automated recall systems by up to 84%. |