# CAREER: From Learning to Forgetting: Linguistic Complexity, Learning Dynamics, and Robustness in Neural Language Models

> **NSF 01002930DB NSF RESEARCH & RELATED ACTIVIT** · University of Massachusetts Lowell (MA) · $487,997

## Abstract

Artificial intelligence systems that generate text now influence how people search for information, learn new skills, obtain health advice, and communicate online. Yet these systems can behave in ways that are hard to predict. They can copy misleading patterns from their training data, produce text that is too complex for a reader's needs, and retain private, outdated, or incorrect content. This project studies how these systems learn, keep, and forget language patterns over time, and uses that knowledge to build systems that are easier to control and safer to use. The results can help create text at appropriate reading levels for second language learners, patients reading health information, and people with communication or cognitive challenges. The project also develops methods to remove harmful patterns without weakening a model's general ability to generate useful text. The project advances reliable artificial intelligence, improves access to understandable information, and trains students through coursework, mentoring, freely available tools, and interdisciplinary workshops to support science and public well-being.

The project develops a linguistically grounded framework for robust and interpretable neural language models. It creates methods for controlled text generation and paraphrasing that allow models to follow user-defined lexical, syntactic, and discourse constraints. These methods combine instruction tuning, explicit control signals, multi-objective optimiza

## Key facts

- **NSF award ID:** 2541273
- **Awardee organization:** University of Massachusetts Lowell (MA)
- **SAM.gov UEI:** LTNVSTJ3R6D5
- **PI:** Hadi Amiri
- **Primary program:** 01002930DB NSF RESEARCH & RELATED ACTIVIT
- **All programs:** Artificial Intelligence (AI), CAREER-Faculty Erly Career Dev
- **Estimated total:** $487,997
- **Funds obligated:** $341,598
- **Transaction type:** Continuing Grant
- **Period:** 07/01/2026 → 06/30/2031

## Primary source

NSF Award Search: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2541273

## Citation

> US National Science Foundation, Award 2541273, CAREER: From Learning to Forgetting: Linguistic Complexity, Learning Dynamics, and Robustness in Neural Language Models. Retrieved via AI Analytics 2026-06-09 from https://api.ai-analytics.org/grant/nsf/2541273. Licensed CC0.

---

*[NSF Awards dataset](/datasets/nsf-awards) · CC0 1.0*