| Challenge: | *Dialz* is a Python library for advancing research on steering vectors for open-source LMs. |
| Approach: | They propose a Python library for advancing research on steering vectors for open-source LMs. |
| Outcome: | The proposed method reduces harmful outputs and provides insights into model behaviour across different layers. |
Similar Papers
AI Steerability 360: A Toolkit for Steering Large Language Models (2026.acl-demo)
Copied to clipboard
Erik Miehling, Karthikeyan Natesan Ramamurthy, Praveen Venkateswaran, Ching-Yun Ko, Pierre Dognin, Moninder Singh, Tejaswini Pedapati, Avinash Balakrishnan, Matthew Riemer, Dennis Wei, Inge Vejsbjerg, Elizabeth M. Daly, Kush R. Varshney
| Challenge: | The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. |
| Approach: | The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. |
| Outcome: | The toolkit is available under an Apache 2.0 license and is available on https://github.com/IBM/AISteer360. |
Style Vectors for Steering Generative Large Language Models (2024.findings-eacl)
Copied to clipboard
Kai Konen, Sophie Jentzsch, Diaoulé Diallo, Peer Schütt, Oliver Bensch, Roxanne El Baff, Dominik Opitz, Tobias Hecking
| 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. |
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. |
Activation Scaling for Steering and Interpreting Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a successful intervention should flip the correct with the wrong token, while remaining sparse. |
| Approach: | They propose to use activation scaling to flip the correct with the wrong token . they use gradient-based optimization to learn and evaluate a specific kind of efficient intervention . |
| Outcome: | The proposed method performs comparable with steering vectors but is much less minimal. |
ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents (2020.acl-demos)
Copied to clipboard
Chia-Yu Li, Daniel Ortega, Dirk Väth, Florian Lux, Lindsey Vanderlyn, Maximilian Schmidt, Michael Neumann, Moritz Völkel, Pavel Denisov, Sabrina Jenne, Zorica Kacarevic, Ngoc Thang Vu
| Challenge: | Existing toolkits for developing dialog systems are limited to core components and do not support multi-modal processing and social signals. |
| Approach: | They propose to use ADVISER to develop multi-modal dialog agents using multi-text and social signals. |
| Outcome: | The proposed toolkit is flexible, easy to use, and easy to extend for linguists and cognitive scientists, thereby providing a flexible platform for collaborative research. |
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent methods for controlling language models can often be classified into three main strategies: prompt engineering, trainable decoding mechanisms, fine-tuning according to specific objectives. |
| Approach: | They evaluate steering vectors for controlling topical focus, sentiment, toxicity, and readability in abstractive summaries across the SAMSum, NEWTS, and arXiv datasets. |
| Outcome: | The proposed method is effective in free-form generation, but high steering strengths induce degenerate repetition and factual hallucinations. |
From Weights to Activations: Is Steering the Next Frontier of Adaptation? (2026.acl-long)
Copied to clipboard
Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, Michael A. Hedderich, Sebastian Lapuschkin, Wojciech Samek, Vera Schmitt
| Challenge: | Pre-trained large language models are the basis of a wide range of NLP tasks. |
| Approach: | They propose to use parameter updates and parameter-efficient adaptation to modify behavior of large language models. |
| Outcome: | The proposed method enables local and reversible behavioral change without parameter updates. |
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) achieve excellent performance through pretraining on extensive data. |
| Approach: | They propose an efficient selective layer intervention based on parameter-efficient fine-tuning methods to select the optimal steering layer to modulate LLM semantics. |
| Outcome: | The proposed approach is based on a model-agnostic framework and is safe to deploy. |
ChartDialogs: Plotting from Natural Language Instructions (2020.acl-main)
Copied to clipboard
| Challenge: | a new dataset of conversational plotting agents is developed to facilitate the development of such agents. |
| Approach: | They propose a dataset that contains over 15,000 dialog turns from matplotlib's most popular plotting library. |
| Outcome: | The proposed system achieves 61% plotting accuracy, compared to the previous method. |
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models (2025.emnlp-demos)
Copied to clipboard
Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang
| Challenge: | Large Language Models (LLMs) have demonstrated extraordinary capabilities, however, they may still generate unreliable or unsafe outputs. |
| Approach: | They propose a framework that allows plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. |
| Outcome: | The framework is designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. |