Can Role Vectors Affect LLM Behaviour? (2025.findings-emnlp)

Copied to clipboard

Challenge: a recent study has shown that personas influence LLM performance, but their direct impact remains unclear.
Approach: They propose a novel approach to guiding LLM behaviour through role vectors . they construct 29 role vector derived from model activations and evaluate their impact .
Outcome: The proposed approach improves in-domain task performance while yielding unexpected gains.

Similar Papers

Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing literature on leveraging persona in large language models is disorganized and lacks a systematic taxonomy . leveraging peopleas has resurfaced as an ideal lens for adapting LLMs for specific contexts .
Approach: They propose to categorize current research on leveraging persona in large language models . they propose to use a comprehensive survey to categorize existing studies .
Outcome: The proposed framework is a promising framework for tailoring large language models to specific contexts.
Style Vectors for Steering Generative Large Language Models (2024.findings-eacl)

Copied to clipboard

Challenge: Large language models (LLMs) can be trained on vast corpora and can generate text in a nuanced and parameterisable way.
Approach: They propose to add style vectors to the activations of hidden layers during text generation to steer output towards specific styles.
Outcome: The proposed approach differs from prompt engineering in that it can be nuanced and parameterisable.
The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead? (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models have shown capabilities close to human performance in various analytical tasks.
Approach: They investigate the efficiency and accuracy of Large Language Models in specialized tasks . they integrate LLMs with expert annotators to observe the impact of LLM suggestions .
Outcome: The proposed model improves task completion speed but introduces anchoring bias . the proposed model is not suitable for open-ended analysis, but is capable of handling specialized tasks.
Dissecting Persona-Driven Reasoning in Language Models via Activation Patching (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas.
Approach: They examine how assigning a persona influences a model’s reasoning on an objective task by activation patching .
Outcome: The early Multi-Layer Perceptron (MLP) layers attend to syntactic structure of input and process its semantic content.
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Copied to clipboard

Challenge: specialized LLMs are often limited in domain-specific applications that require specialized knowledge.
Approach: They provide a comprehensive overview of four key methods to enhance large language models by integrating domain-specific knowledge.
Outcome: The proposed methods are categorized into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization.
When ”A Helpful Assistant” Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Commercial AI systems often define the role of the LLM in system prompts.
Approach: They conduct a systematic evaluation of personas in system prompts by adding 162 roles covering 6 types of interpersonal relationships and 8 domains of expertise.
Outcome: The proposed model does not improve performance in the system prompt setting where no persona is added.
Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Despite efforts to mitigate social bias in large language models, representational harms such as stereotyping continue to exist in both open and closed-source models.
Approach: They propose a method to modify model activations in forward passes by applying steering vectors to a BBQ dataset and comparing their results to bias mitigation methods.
Outcome: The proposed method outperforms 3 other bias mitigation methods on the BBQ dataset and shows the lowest impact on MMLU scores.
Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications.
Approach: They propose a reliable strategy for domains to choose more robust LLMs for real-world applications.
Outcome: The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications.
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction.
Approach: They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance.
Outcome: The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies.
Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance (2025.emnlp-main)

Copied to clipboard

Challenge: Prior work on persona prompting has shown mixed results on its effectiveness . prior work did not consider when and why personas should affect performance .
Approach: They analyze literature on persona prompting and distill three desiderata for their effectiveness . they propose mitigation strategies to improve robustness but find they only work for the largest, most capable models .
Outcome: The authors find that expert personas usually lead to positive or non-significant performance changes . they propose mitigation strategies to improve robustness but only for the largest models .

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