Papers by Anna-Carolina Haensch

6 papers
Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing studies focus on generating closed-ended survey responses with large language models, whereas LLMs are typically trained to generate open-ended text.
Approach: They evaluate the impact of various Survey Response Generation Methods on simulated responses by generating closed-ended responses from large language models.
Outcome: The proposed methods perform best in individual-level and subpopulation-level alignment.
Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation (2026.eacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly used to simulate public opinion and other social phenomena.
Approach: They argue that open-endedness is essential for realistic social simulations . they argue that it captures expressiveness and individuality .
Outcome: The proposed frameworks can improve measurement and design, support exploration of unanticipated views, and reduce researcher-imposed directive bias.
The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models have sparked interest in validating human-like cognitive-behavioral traits.
Approach: They examine whether LLM outputs reflect human-like cognitive-behavioral traits . they find that measuring AOVs embedded within LLMs remains opaque .
Outcome: The proposed model can be used to evaluate human-like cognitive-behavioral traits . the proposed model could be used in writing assistants and other applications .
Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have generated significant interest in their potential for synthetic data generation across various domains.
Approach: They use open-ended survey data from the German Longitudinal Election Studies to prompt different LLMs to generate synthetic public opinions reflective of German subpopulations by incorporating demographic features into the persona prompts.
Outcome: The LLM performs better for supporters of left-leaning parties like The Greens and The Left compared to other parties, and matches the least with the right-party AfD.
Can Large Language Models Advance Crosswalks? The Case of Danish Occupation Codes (2025.naacl-srw)

Copied to clipboard

Challenge: Large Language Models (LLMs) are used to map classification systems to each other . however, their use is labor-intensive and requires domain expertise .
Approach: They propose a prompt-based framework where LLMs perform similarity assessments between classification codes and identify final mappings through a guided decision process.
Outcome: The proposed framework shows that LLMs perform better than the embedding-based framework in creating crosswalks.
Capabilities and Evaluation Biases of Large Language Models in Classical Chinese Poetry Generation: A Case Study on Tang Poetry (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly applied to creative domains, yet performance in classical Chinese poetry generation and evaluation remains poorly understood.
Approach: They propose a framework that combines computational metrics, LLM-as-a-judge assessment, and human expert validation to evaluate large language models.
Outcome: The proposed framework evaluates state-of-the-art LLMs across multiple dimensions of poetic quality in Tang poetry generation.

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