# Collaborative Research: Research: CompCog: RI: Medium: Semantic Focusing: Controlling LM Interpretations for Human-Model Alignment

> **NSF 01002526DB NSF RESEARCH & RELATED ACTIVIT** · New York University (NY) · $763,741

## Abstract

How do people derive meaning from sentences? In what situations does the language comprehension process break down? Artificial intelligence (AI) language models such as ChatGPT, which appear to understand and use language as proficiently as humans do, might seem poised to provide potential answers to this question—answers that could not only enrich our scientific understanding, but also help address language processing deficits. But for AI systems to fully realize this potential, they need to process language in a similar way to humans. Many distinct lines of research show that this is not the case. One area where the discrepancy between humans and AI is particularly pronounced concerns temporary semantic ambiguity in language: cases where the first few words of the sentence are consistent with multiple interpretations, and only later in the sentence is it clear which of the interpretations is the correct one. Whereas human readers can encounter significant difficulty when they are required to change their interpretation of a sentence, AI models generally do not. The goal of this project is to better understand the reason for this misalignment between humans and AI models, and explore ways of modifying AI architectures to bring them more in line with how humans process language. In this project, the researchers will benchmark success in their model development by comparing how the models process language to how humans process language using a variety of psycholinguistic measu

## Key facts

- **NSF award ID:** 2504953
- **Awardee organization:** New York University (NY)
- **SAM.gov UEI:** NX9PXMKW5KW8
- **PI:** Tal Linzen
- **Primary program:** 01002526DB NSF RESEARCH & RELATED ACTIVIT
- **All programs:** ROBUST INTELLIGENCE, MEDIUM PROJECT
- **Estimated total:** $763,741
- **Funds obligated:** $763,741
- **Transaction type:** Standard Grant
- **Period:** 09/01/2025 → 08/31/2029

## Primary source

NSF Award Search: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2504953

## Citation

> US National Science Foundation, Award 2504953, Collaborative Research: Research: CompCog: RI: Medium: Semantic Focusing: Controlling LM Interpretations for Human-Model Alignment. Retrieved via AI Analytics 2026-06-08 from https://api.ai-analytics.org/grant/nsf/2504953. Licensed CC0.

---

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