Papers by Taylor Sorensen

8 papers
Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models (2022.findings-emnlp)

Copied to clipboard

Challenge: We explore the idea of compressing the prompts used to condition language models.
Approach: They explore the idea of compressing the prompts used to condition language models . they show that compressed prompts can retain a substantive amount of information about the original prompt .
Outcome: The proposed method can be extended to controllability and toxicity reduction.
Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model (2024.naacl-long)

Copied to clipboard

Challenge: Impossible Distillation is a framework for paraphrasing and sentence summarization that can be trained from a low-quality teacher model.
Approach: They propose a framework that distills a high-quality dataset from a low-quality teacher . they hypothesize and verify the paraphrastic proximity intrinsic to pre-trained LMs .
Outcome: The proposed framework outperforms baseline models on unconstrained paraphrase generation and sentence summarization benchmarks.
NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation (2023.findings-emnlp)

Copied to clipboard

Challenge: a new commonsense knowledge model, NovaCOMET, combines knowledge and general task models.
Approach: They propose an open commonsense knowledge model that combines knowledge and general task models.
Outcome: The proposed model matches or exceeds existing knowledge models on commonsense reasoning tasks.
An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels (2022.acl-long)

Copied to clipboard

Challenge: Existing prompt engineering methods require labeled data and access to model parameters . a new method for selecting prompt templates without labeles and without direct access to the model is needed.
Approach: They propose a method for selecting prompt templates without labeled examples and without direct access to the model.
Outcome: The proposed method performs at almost oracle levels, without labels, on 7 datasets representing 7 different NLP tasks.
Can Language Models Reason about Individualistic Human Values and Preferences? (2025.acl-long)

Copied to clipboard

Challenge: Existing methods and evaluation frameworks for achieving pluralistic alignment are limited by the diversity of people, which is pre-specified and coarsely categorized, papering over individuality.
Approach: They propose to use a dataset transformed from the influential World Values Survey to study language models on the specific challenge of individualistic value reasoning.
Outcome: The proposed model can predict individualistic values with accuracies between 55% and 65%, while a precise description of individualistic value judgments cannot be approximated only via demographic information.
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration (2024.emnlp-main)

Copied to clipboard

Challenge: Existing alignment paradigms for large language models learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities.
Approach: They propose a modular framework that "plugs" into a base LLM a pool of smaller but specialized community LMs where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional.
Outcome: The proposed framework “plugs into” a base LLM a pool of smaller but specialized community LMs, where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional.
Value Profiles for Encoding Human Variation (2025.emnlp-main)

Copied to clipboard

Challenge: Using value profiles and a steerable decoder model to estimate ratings is crucial for personalization, pluralistic model alignment, and computational social science.
Approach: They propose to represent individuals using value profiles and a steerable decoder model to estimate ratings conditioned on a value profile or other rater information.
Outcome: The proposed model interpretably changes ratings according to semantic profile differences and is well-calibrated.
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Lack of transparency in training data is limiting external oversight and inspection of LLMs for issues such as copyright infringement and data contamination.
Approach: They propose a method to identify training data known to proprietary LLMs without requiring access to model weights or token probabilities by using information-guided probes.
Outcome: The proposed method can identify training data known to proprietary LLMs without access to model weights or token probabilities.

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