Papers by Zexin Ma
PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing alignment methods struggle to balance general reasoning with instruction-following (IF) this is hindered by dependency on teacher models, reward hacking, and reasoning-answer inconsistencies. |
| Approach: | They propose a two-stage curriculum learning framework based on Reinforcement Learning from Verifiable Rewards to enhance both IF and general reasoning capabilities. |
| Outcome: | The proposed framework outperforms leading models on six representative IF tasks while achieving a 21.25% relative average improvement over the original model. |
EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for accelerating Large Vision-Language Models lack comprehensive evaluation across diverse backbones, benchmarks, and metrics. |
| Approach: | They propose EffiVLM-BENCH framework for evaluating absolute performance and generalization and loyalty. |
| Outcome: | The proposed framework offers insights into optimal strategies for accelerating LVLMs. |
Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that large language models can perform precise text editing tasks. |
| Approach: | InstrEditBench is a benchmark dataset that compares 30,000 structured editing tasks . experimental evaluations show FineEdit outperforms state-of-the-art models . |
| Outcome: | The proposed model outperforms state-of-the-art models on single-turn edits and mistral-7B-OpenOrca on direct edits. |
Narrative Style and the Spread of Health Misinformation on Twitter (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Using a narrative style is an effective way to communicate health information on and off social media platforms. |
| Approach: | They annotate health misinformation tweets and classify them into narrative and non-narrative . they then use supervised fine-tuning and in-context learning to detect narratives . |
| Outcome: | The proposed model analyzes health misinformation tweets and finds that narrative use is linked to increased tweet engagement and can lead to increased misinformation use. |
Social Story Frames: Contextual Reasoning about Narrative Intent and Reception (2026.acl-long)
Copied to clipboard
Joel Mire, Maria Antoniak, Steven R Wilson, Zexin Ma, Achyutarama R Ganti, Andrew Piper, Maarten Sap
| Challenge: | SocialStoryFrames is a formalism for distilling plausible inferences about reader response . authors characterize frequency and interdependence of storytelling intents across communities . |
| Approach: | They propose a formalism for distilling plausible inferences about reader response using conversational context and a taxonomy grounded in narrative theory, linguistic pragmatics, and psychology. |
| Outcome: | The proposed model can be used to analyze reader responses in online communities. |