Fetching the paper…

Reading the bibliography…

2025

Controlling Large Language Models Through Concept Activation Vectors

Zhang, Hanyu, Wang, Xiting, Li, Chengao et al.

Original
PDF
Post on X

Understand

As large language models (LLMs) are widely deployed across various domains, the ability to control their generated outputs has become more critical.

This control involves aligning LLMs outputs with human values and ethical principles or customizing LLMs on specific topics or styles for individual users.
Existing controlled generation methods either require significant computational resources and extensive trial-and-error or provide coarse-grained control.
In this paper, we propose Generation with Concept Activation Vector (GCAV), a lightweight model control framework that ensures accurate control without requiring resource-extensive fine-tuning.

Controlling Large Language Models Through Concept Activation Vectors · Around

Built on

Language Models are Few-Shot Learners
Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J. D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; Agarwal, S.; Herbert-Voss, A.; Krueger, G.; Henighan, T.; Child, R.; Ramesh, A.; Ziegler, D.; Wu, J.; Winter, C.; Hesse, C.; Chen, M.; Sigler, E.; Litwin, M.; Gray, S.; Chess, B.; Clark, J.; Berner, C.; McCandlish, S.; Radford, A.; Sutskever, I.; and Amodei, D. 2020a · 1901
Earlier work this paper cites.
Language models are few-shot learners
Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J. D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. 2020b · 1901
Earlier work this paper cites.
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Original
Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; Levy, O.; Lewis, M.; Zettlemoyer, L.; and Stoyanov, V. 2019 · 1907
Earlier work this paper cites.
Learning word vectors for sentiment analysis
Maas, A.; Daly, R. E.; Pham, P. T.; Huang, D.; Ng, A. Y.; and Potts, C. 2011 · 2011
Earlier work this paper cites.
Proximal policy optimization algorithms
Original
Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; and Klimov, O. 2017 · 2017
Earlier work this paper cites.
Bert: Pre-training of deep bidirectional transformers for language understanding
Original
Devlin, J. 2018 · 2018
Earlier work this paper cites.
Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)
Kim, B.; Wattenberg, M.; Gilmer, J.; Cai, C.; Wexler, J.; Viegas, F.; et al. 2018 · 2018
Earlier work this paper cites.
Deep Contextualized Word Representations
Peters, M. E.; Neumann, M.; Iyyer, M.; Gardner, M.; Clark, C.; Lee, K.; and Zettlemoyer, L. 2018 · 2018
Earlier work this paper cites.
Practical optimization
Gill, P. E.; Murray, W.; and Wright, M. H. 2019 · 2019
Earlier work this paper cites.
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
Dathathri, S.; Madotto, A.; Lan, J.; Hung, J.; Frank, E.; Molino, P.; Yosinski, J.; and Liu, R. 2020 · 2020
Earlier work this paper cites.
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S.; Gururangan, S.; Sap, M.; Choi, Y.; and Smith, N. A. 2020 · 2020
Earlier work this paper cites.
SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python
Virtanen, P.; Gommers, R.; Oliphant, T. E.; Haberland, M.; Reddy, T.; Cournapeau, D.; Burovski, E.; Peterson, P.; Weckesser, W.; Bright, J.; van der Walt, S. J.; Brett, M.; Wilson, J.; Millman, K. J.; Mayorov, N.; Nelson, A. R. J.; Jones, E.; Kern, R.; Larson, E.; Carey, C. J.; Polat, İ.; Feng, Y.; Moore, E. W.; VanderPlas, J.; Laxalde, D.; Perktold, J.; Cimrman, R.; Henriksen, I.; Quintero, E. A.; Harris, C. R.; Archibald, A. M.; Ribeiro, A. H.; Pedregosa, F.; van Mulbregt, P.; and SciPy 1.0 Contributors. 2020 · 2020
Earlier work this paper cites.
Prefix-tuning: Optimizing continuous prompts for generation
Original
Li, X. L.; and Liang, P. 2021 · 2021
Earlier work this paper cites.
FUDGE: Controlled Text Generation With Future Discriminators
Yang, K.; and Klein, D. 2021 · 2021
Earlier work this paper cites.
Training language models to follow instructions with human feedback
Ouyang, L.; Wu, J.; Jiang, X.; Almeida, D.; Wainwright, C.; Mishkin, P.; Zhang, C.; Agarwal, S.; Slama, K.; Ray, A.; et al. 2022 · 2022
Earlier work this paper cites.

Similar

Tailor: A prompt-based approach to attribute-based controlled text generation
Original
Yang, K.; Liu, D.; Lei, W.; Yang, B.; Xue, M.; Chen, B.; and Xie, J. 2022 · 2022
Cited alongside, same era.
Don’t Lose the Message While Paraphrasing: A Study on Content Preserving Style Transfer
Babakov, N.; Dale, D.; Gusev, I.; Krotova, I.; and Panchenko, A. 2023 · 2023
Cited alongside, same era.
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
Bang, Y.; Cahyawijaya, S.; Lee, N.; Dai, W.; Su, D.; Wilie, B.; Lovenia, H.; Ji, Z.; Yu, T.; Chung, W.; et al. 2023 · 2023
Cited alongside, same era.
Combating misinformation in the age of llms: Opportunities and challenges
Chen, C.; and Shu, K. 2023 · 2023
Cited alongside, same era.
Palm: Scaling language modeling with pathways
Chowdhery, A.; Narang, S.; Devlin, J.; Bosma, M.; Mishra, G.; Roberts, A.; Barham, P.; Chung, H. W.; Sutton, C.; Gehrmann, S.; et al. 2023 · 2023
Cited alongside, same era.

Then

Linear representations of sentiment in large language models
Original
Tigges, C.; Hollinsworth, O. J.; Geiger, A.; and Nanda, N. 2023 · 2023
Later among the works it cites.
Llama 2: Open foundation and fine-tuned chat models
Original
Touvron, H.; Martin, L.; Stone, K.; Albert, P.; Almahairi, A.; Babaei, Y.; Bashlykov, N.; Batra, S.; Bhargava, P.; Bhosale, S.; et al. 2023 · 2023
Later among the works it cites.
Activation addition: Steering language models without optimization
Original
Turner, A.; Thiergart, L.; Udell, D.; Leech, G.; Mini, U.; and MacDiarmid, M. 2023 · 2023
Later among the works it cites.
A survey of controllable text generation using transformer-based pre-trained language models
Zhang, H.; Song, H.; Li, S.; Zhou, M.; and Song, D. 2023 · 2023
Later among the works it cites.
Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Controlled Text Generation via Language Model Arithmetic

Dekoninck, J.; Fischer, M.; Beurer-Kellner, L.; and Vechev, M. 2023 · 2023

Cited alongside, same era.

More than a Feeling: Accuracy and Application of Sentiment Analysis

Hartmann, J.; Heitmann, M.; Siebert, C.; and Schamp, C. 2023 · 2023

Cited alongside, same era.

Chatdb: Augmenting llms with databases as their symbolic memory

Hu, C.; Fu, J.; Du, C.; Luo, S.; Zhao, J.; and Zhao, H. 2023 · 2023

Cited alongside, same era.

Can large language models truly understand prompts? a case study with negated prompts

Jang, J.; Ye, S.; and Seo, M. 2023 · 2023

Cited alongside, same era.

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Li, K.; Hopkins, A. K.; Bau, D.; Viégas, F.; Pfister, H.; and Wattenberg, M. 2023 · 2023

Cited alongside, same era.

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Liu, S.; Ye, H.; Xing, L.; and Zou, J. Y. 2023 · 2023

Cited alongside, same era.

Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Nanda, N.; Lee, A.; and Wattenberg, M. 2023 · 2023

Cited alongside, same era.

Zhong, T.; Wang, Q.; Han, J.; Zhang, Y.; and Mao, Z. 2023 · 2023

Later among the works it cites.

Representation engineering: A top-down approach to ai transparency

Zou, A.; Phan, L.; Chen, S.; Campbell, J.; Guo, P.; Ren, R.; Pan, A.; Yin, X.; Mazeika, M.; Dombrowski, A.-K.; et al. 2023 · 2023

Later among the works it cites.

Can Large Language Models Detect Misinformation in Scientific News Reporting?

Original

Cao, Y.; Nair, A. M.; Eyimife, E.; Soofi, N. J.; Subbalakshmi, K.; Wullert II, J. R.; Basu, C.; and Shallcross, D. 2024 · 2024

Later among the works it cites.

Bias and fairness in large language models: A survey

Gallegos, I. O.; Rossi, R. A.; Barrow, J.; Tanjim, M. M.; Kim, S.; Dernoncourt, F.; Yu, T.; Zhang, R.; and Ahmed, N. K. 2024 · 2024

Later among the works it cites.

Long-context llms struggle with long in-context learning

Original

Li, T.; Zhang, G.; Do, Q. D.; Yue, X.; and Chen, W. 2024 · 2024

Later among the works it cites.

PaCE: Parsimonious Concept Engineering for Large Language Models

Luo, J.; Ding, T.; Chan, K. H. R.; Thaker, D.; Chattopadhyay, A.; Callison-Burch, C.; and Vidal, R. 2024 · 2024

Later among the works it cites.

A systematic survey of prompt engineering in large language models: Techniques and applications

Sahoo, P.; Singh, A. K.; Saha, S.; Jain, V.; Mondal, S.; and Chadha, A. 2024 · 2024

Later among the works it cites.

REPLUG: Retrieval-Augmented Black-Box Language Models

Shi, W.; Min, S.; Yasunaga, M.; Seo, M.; James, R.; Lewis, M.; Zettlemoyer, L.; and Yih, W.-t. 2024 · 2024

Later among the works it cites.

Function Vectors in Large Language Models

Todd, E.; Li, M.; Sharma, A.; Mueller, A.; Wallace, B. C.; and Bau, D. 2024 · 2024

Later among the works it cites.

Uncovering Safety Risks in Open-source LLMs through Concept Activation Vector

Xu, Z.; Huang, R.; Wang, X.; Wu, F.; Yao, J.; and Xie, X. 2024 · 2024

Later among the works it cites.

Tree of thoughts: Deliberate problem solving with large language models

Yao, S.; Yu, D.; Zhao, J.; Shafran, I.; Griffiths, T.; Cao, Y.; and Narasimhan, K. 2024 · 2024

Later among the works it cites.