Steering Llama 2 via Contrastive Activation Addition

Open Problems in Mechanistic Interpretability

Sharkey, L., Chughtai, B., Batson, J., Lindsey, J., Wu, J., Bushnaq, L., Goldowsky-Dill, N., Heimersheim, S., Ortega, A., Bloom, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.16496 · Cited by 291

Conversate: Supporting Reflective Learning in Interview Practice Through Interactive Simulation and Dialogic Feedback

Daryanto, T., Ding, X., Wilhelm, L. A., Stil, S., Knutsen, K. M., & Rho, E. H. R. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3701188 · Cited by 67

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

Wang, P., Zhang, D., Li, L., Tan, C., Wang, X., Zhang, M., Ren, K. L., Jiang, B., & Qiu, X. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.585 · Cited by 38

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Templeton, A., Conerly, T., Marcus, J., Lindsey, J., Bricken, T., Chen, B., Pearce, A., Citro, C., Ameisen, E., Jones, A., et al. (2026) · arXiv · doi:10.48550/arxiv.2605.29358 · Cited by 36

Fostering effective hybrid human-LLM reasoning and decision making

Passerini, A., Gema, A. P., Minervini, P., Sayin, B., & Tentori, K. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1464690 · Cited by 39

Simulating Subjects: The Promise and Peril of Artificial Intelligence Stand-Ins for Social Agents and Interactions

Kozlowski, A. C., & Evans, J. A. (2025) · Sociological Methods & Research · doi:10.1177/00491241251337316 · Cited by 49

AI–AI bias: Large language models favor communications generated by large language models

Laurito, W., Davis, B., Grietzer, P., Gavenčiak, T., Böhm, A., & Kulveit, J. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2415697122 · Cited by 32

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

Tsui, K. (2025) · arXiv · doi:10.48550/arxiv.2507.02778 · Cited by 29

Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering

Valentino, M., Kim, G., Dalal, D., Zhao, Z., & Freitas, A. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i39.40617 · Cited by 27

Cognitive LLMs: Toward Human-Like Artificial Intelligence by Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-Making

Wu, S., Oltramari, A., Francis, J., Giles, C. L., & Ritter, F. E. (2025) · Neurosymbolic Artificial Intelligence · doi:10.1177/29498732251377341 · Cited by 30

Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective

Gabison, G. A., & Xian, R. P. (2025) · Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025) · doi:10.18653/v1/2025.realm-1.9 · Cited by 19

The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis

Mueller, A., Brinkmann, J., Li, M., Marks, S., Pal, K., Prakash, N., Rager, C., Sankaranarayanan, A., Sharma, A. S., Sun, J., et al. (2025) · Computational Linguistics · doi:10.1162/coli.a.572 · Cited by 65

The AI Alignment Paradox

West, R., & Aydin, R. C. (2025) · Communications of the ACM · doi:10.1145/3705294 · Cited by 13

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks

Wang, H., Gang, W., & Zhang, H. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02787 · Cited by 28

Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing

Wang, H., Yue, Y., Lu, R., Shi, J., Zhao, A., Wang, S., Song, S., & Huang, G. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.321 · Cited by 22

When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models

Wang, K., Li, J., Yang, S., Zhang, Z., & Wang, D. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i39.40645 · Cited by 8

Steerable Chatbots: Exploring Direct Manipulation Interfaces for LLM Personalization via Activation Steering

Bo, J. Y., Xu, T., Chatterjee, I., Passarella-Ward, K., Kulshrestha, A., & Shin, D. (2026) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3830398.3830533 · Cited by 24

Improving Instruction-Following in Language Models through Activation SteeringPreprint

Stolfo, A., Balachandran, V., Yousefi, S., Horvitz, E., & Nushi, B. (2024) · Qeios · doi:10.32388/btht4k · Cited by 12

LLM-ACTR: from Cognitive Models to LLMs in Manufacturing Solutions

Wu, S., Oltramari, A., Francis, J., Giles, C. L., & Ritter, F. E. (2025) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v5i1.35610 · Cited by 5

Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State Intervention

Su, J., Chen, J., Li, H., Chen, Y., Li, Q., & Zhang, Z. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.634 · Cited by 15

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

Zhao, W., Guo, J., Hu, Y., Deng, Y., Zhang, A., Sui, X., Han, X., Zhao, Y., Qin, B., Chua, T., et al. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1248 · Cited by 32

Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models

Adiga, R., Nushi, B., & Chandrasekaran, V. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.1281 · Cited by 10

Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models

Qian, C., Zhang, J., Yao, W., Liu, D., Yin, Z., Qiao, Y., Liu, Y., & Shao, J. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.290 · Cited by 12

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks

Yi, X., Li, Y., Shi, D., Wang, L., Wang, X., & He, L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129101 · Cited by 8

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis

Yang, Y., Sondej, F., Mayne, H., Lee, A., & Mahdi, A. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1501 · Cited by 8

Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories

Beigi, M., Shen, Y., Shojaee, P., Wang, Q., Wang, Z., Reddy, C. K., Jin, M., & Huang, L. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.661 · Cited by 11

Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models

Yang, J., Li, R., Wang, W., Zhou, Z., Feng, Z., & Peng, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3346-6_13 · Cited by 14

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

Li, Z., Wang, X., Yang, Y., Yao, Z., Xiong, H., & Du, M. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.552 · Cited by 12

Elements of World Knowledge ( EWoK ): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models

Ivanova, A. A., Sathe, A., Lipkin, B., Kumar, U., Radkani, S., Clark, T. H., Kauf, C., Hu, J., Pramod, R. T., Grand, G., et al. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.38 · Cited by 7

Steering LLM Reasoning Through Bias-Only Adaptation

Sinii, V., Gorbatovski, A., Cherepanov, A., Shaposhnikov, B., Balagansky, N., & Gavrilov, D. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.467 · Cited by 3

Toward universal steering and monitoring of AI models

Beaglehole, D., Radhakrishnan, A., Boix-Adserà, E., & Belkin, M. (2026) · Science · doi:10.1126/science.aea6792 · Cited by 33

Evaluating the Prompt Steerability of Large Language Models

Miehling, E., Desmond, M. J., Ramamurthy, K. N., Daly, E., Varshney, K. R., Farchi, E., Dognin, P., Ríos, J., Bouneffouf, D., Liu, M., et al. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.400 · Cited by 7

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

Li, Y., Fan, Z., Chen, R., Gai, X., Gong, L., Zhang, Y., & Liu, Z. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.589 · Cited by 9

“Reasoning” with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments

Verma, P., Jaidka, K., & Churina, S. (2025) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v19i1.35913 · Cited by 7

Do Transformer Interpretability Methods Transfer to RNNs?

Paulo, G., Marshall, T., & Belrose, N. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i26.34969 · Cited by 12

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy

Feng, Z., Chen, Z., Ma, J., Po, Y. T., Chersoni, E., & Li, B. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.1126 · Cited by 2

Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations

Ji, Z., Lei, Y., Koishekenov, Y., Bang, Y., Hartshorn, A., Schelten, A., Zhang, C., Fung, P., & Cancedda, N. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.187 · Cited by 10

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction

Zhang, J., Liu, N., Fan, Y., Huang, Z., Zeng, Q., Cai, K., Wang, J., & Wang, K. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i41.40776 · Cited by 11

Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning

Zhang, J., Wang, J., Qiang, W., Xu, F., & Zheng, C. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792374 · Cited by 5

Discovering consumer sentiment in E-commerce conversations: A dialogue graph attention network approach

Liu, Y., Huang, J., Zhang, C., & Peng, M. (2026) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2026.101606 · Cited by 2

From Weights to Activations: Is Steering the Next Frontier of Adaptation?

Ostermann, S., Gurgurov, D., Baeumel, T., Hedderich, M. A., Lapuschkin, S., Samek, W., & Schmitt, V. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.1377 · Cited by 5

Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective

Pham, V.-C., & Nguyen, T. H. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.761 · Cited by 15

Learning Task Representations from In-Context Learning

Sağlam, B., Hu, X., Yang, Z., Kalogerias, D. S., & Karbasi, A. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.345 · Cited by 2

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

Zhao, H., Wu, X., Yang, F., Shen, B., Liu, N., & Du, M. (2026) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2026.findings-eacl.40 · Cited by 6

EasyDetector: Using Linear Probe to Detect the Provenance of Large Language Models

Zhang, J., Li, J., Fei, H., Li, L., & Zhu, H. (2024) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom63139.2024.00333 · Cited by 2

Repairing LLM Executions for Secure Automatic Programming

Husseini, A. E., Izza, Y., Genest, B., & Roychoudhury, A. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3773210 · Cited by 1

Guillotine: Hypervisors for Isolating Malicious AIs

Mickens, J. W., Radway, S., & Netravali, R. (2025) · Workshop on Hot Topics in Operating Systems · doi:10.1145/3713082.3730391 · Cited by 1

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

Shairah, H. A., Hammoud, H. A. A. K., Turkiyyah, G. M., & Ghanem, B. (2026) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/2026.emnlp-main.75 · Cited by 6

A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs

Ghosh, S., Bhattacharjee, A., Ziser, Y., & Parisien, C. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1781 · Cited by 1

Understanding Refusal in Language Models with Sparse Autoencoders

Yeo, W. J., Prakash, N., Neo, C., Satapathy, R., Lee, R. K.-W., & Cambria, E. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.338 · Cited by 1

SHARP: Steering Hallucination in LVLMs via Representation Engineering

Wu, J., Ding, Y., Liu, G., Xia, T., Huang, Z., Sui, D., Liu, Q., Wu, S., Wang, L., & Tan, T. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.725 · Cited by 1

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors

Cao, B., Li, C., Cao, Y., Ge, Y., Wang, T., & Chen, J. (2025) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3719027.3765124 · Cited by 5

Beyond Multiple Choice: Evaluating Steering Vectors for Summarization

Braun, J., Eickhoff, C., & Bahrainian, S. A. (2026) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2026.findings-eacl.200 · Cited by 1

Erasing Your Voice Before it’s Heard: Training-Free Speaker Unlearning for Zero-Shot Text-to-Speech

Lee, M., Shin, E., & Lee, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462017 · Cited by 3

Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs

Tang, W., Wan, Z., Komamizu, T., & Ide, I. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1947-6_33 · Cited by 2

Causal evidence that language models use confidence to drive behaviour

Kumaran, D., Daw, N. D., Osindero, S., Veličković, P., & Pătrăucean, V. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01293-x · Cited by 1

Fine-Grained Interpretation of Political Opinions in Large Language Models

Hu, J., Yang, M., Du, M., & Liu, W. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i45.41199 · Cited by 2

Latent-Space Adversarial Training with Post-Aware Calibration for Defending Large Language Models Against Jailbreak AttacksPreprint

Yi, X., Li, Y., Wang, L., Wang, X., & He, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5169050 · Cited by 1

ARCADE: Controllable Codon Design from Foundation Models via Activation EngineeringPreprint

Li, J., Lai, H.-S., Liang, L., Du, S., Tang, S., & Kingsford, C. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.19.668819 · Cited by 1

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Wu, Z., Arora, A., Geiger, A., Wang, Z., Huang, J., Jurafsky, D., Manning, C. D., & Potts, C. (2025) · arXiv · doi:10.48550/arxiv.2501.17148

Instruction Following by Principled Boosting Attention of Large Language Models

Guardieiro, V., Khare, A., Stein, A., & Wong, E. (2025) · arXiv · doi:10.48550/arxiv.2506.13734

Hidden Pieces: An Analysis of Linear Probes for GPT Representation Edits

Davis, A., & Sukthankar, G. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00073 · Cited by 2

Beyond Stochastic Parroting: LLMs' Human-Like Behavioral Biases Emerge from Linear Neural RepresentationsPreprint

Leng, Y., & Nguyen, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5170182

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning

Olmo, J., Wilson, J., Forsey, M., Hepner, B., Howe, T. V., & Wingate, D. (2025) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2025.findings-naacl.423

Steering Vector Fields for Property-Controlled Molecular Generation with Chemical Language ModelsPreprint

Dimitrievikj, A., & Wells, J. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.24.678080

The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation

Diallo, D., Dworatzyk, K., Jentzsch, S. F., Schütt, P., Theis, S., & Hecking, T. (2025) · IEEE Access · doi:10.1109/access.2025.3628500 · Cited by 2

Alignment with Psychological Concept Network

Hamada, H. T., & Harada, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4384-7_36

Linear Steerability in Language Models: When It Emerges and How It Evolves

She, J., Li, X., Xing, E. P., Liu, Z., & Ho, Q. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.969

Where Confabulation Lives: Latent Feature Discovery in LLMs

Ardoin, T., Cai, Y., & Wunder, G. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1515 · Cited by 1

Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language Models

Cho, I., & Hockenmaier, J. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1474

Neuron-Level Differentiation of Memorization and Generalization in Large Language Models

Huang, K.-W., Fu, Y.-F., Tsai, C., Tu, Y.-C., Cheng, T.-L., Lin, C.-Y., Yang, Y., Liu, H.-Y., Liao, K.-T., Juan, D.-C., et al. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.812

Beyond Demonstrations: Dynamic Vector Construction from Latent Representations

Cai, W., Huang, H.-Y., Wang, Z., & Wu, Y. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.297 · Cited by 2

Reinforcement Learning-based Collaborative Attention Head Selection MethodPreprint

Zhang, J., Hu, Y., Zhou, Y., Liu, B., Liu, T., & Li, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5800462

Exploring the Limits of Probes for Latent Representation Edits in GPT Models

Davis, A. L., Ferrer, R. V., & Sukthankar, G. (2026) · AI · doi:10.3390/ai7030092

Steering Representations, Safeguarding Privacy: A Cross-Modal Privacy Protection Method for Generative AI

Zhang, J. M., Niu, C., Nan, Z., Xu, Y., & Weng, J. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i41.40773

Controllable Epistemic Sensitivity in Large Language Models: Probing, Benchmarking, and Adaptive Reasoning

Srivarshinee, S. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i48.42322

Safe-Unsafe Concept Separation Emerges from a Single Direction in Language Models Activation Space

Ermellino, A., Malandri, L., Mercorio, F., & Serino, A. (2026) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2026.eacl-long.139

Tutorial on Mechanistic Interpretability

Chen, C., Heuss, M., & Eickhoff, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21321-1_6

Feature Drift: How Fine-Tuning Repurposes Representations in LLMs

Galichin, A. V., Korznikov, A., Dontsov, A., Rogov, O. Y., Tutubalina, E., & Oseledets, I. (2026) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2026.findings-eacl.96

PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under a Subspace Calibration

Yu, M., Li, H., Singh, P., Li, X., Wang, D., & Hu, L. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792273 · Cited by 11

IConMoE: Modeling Intents of Misinformation using Concept Activation Vector-based Mixture of Experts

Singh, A. K., & Mishra, R. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792582

Latent manipulator: using concept-guided embedding manipulation to steer embedding visualizations

Raval, S., Dunnell, K., & Lippman, A. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798816

CLEAN: Compliant Loops with Enhanced Adjustment for Training-Free Unlearning

Pu, J., Guo, J., Li, Y., Wang, Z., & Tian, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463950

EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis

Zhou, L., Jiang, H., Li, J., Wang, T., & Li, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464460

What If AI Lived Inside Your Mind? Simulating “Neural Integration” of Human and AI through Mechanistic Interpretability as Provocation

Pataranutaporn, P., Albrecht, C., Archiwaranguprok, C., Karny, S., & Baez, A. (2026) · Augmented Humans International Conference (AHs) · doi:10.1145/3795011.3795070

Decoding and controlling emotion in LLMs through human-aligned representational geometry with enhanced interpretability

Wu, X., Wang, H., Yan, Z., Xiaohan, T., Xu, P., Siok, W. T., Li, P., Gao, J., Lyu, B., & Qin, L. (2026) · Computers in Human Behavior · doi:10.1016/j.chb.2026.109051

Dual-space Sparse Mask Injection: A Defense Framework for Large Language Models Against Jailbreak Attacks

Deng, X., & Cai, R. (2026) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1109/gaiis69281.2026.11519321

Whose Politics Do LLMs Represent? Uncovering Political Bias in LLMs’ Latent Space: A Case Study in Australia

Ruidias, R. R. S., Nunes, B. P., & da Silva, T. N. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1468-6_27

Disentangling Style and Semantics for Calendar-Driven Text Generation: A Knowledge Graph-Guided Activation Steering Approach

Shrivastava, T., Bajpai, A., & Mundotiya, R. K. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1468-6_42

Test-Time Improvement for Large Models: A Survey of Inference-Stage Mechanisms, Resource Control, and Research OpportunitiesPreprint

Tang, Y., Liu, Z., Chen, Z., Yang, J., Xiang, L., Xu, Z., & He, Z. (2026) · Research Square · doi:10.21203/rs.3.rs-9875246/v1

UAD-ICL: Uncertainty-aware semantic control for trustworthy latent context in-context learning

Zhang, J., Hu, Y., Liu, T., Liu, B., Zhang, Z., & Liu, H. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114241

The broken mirror: structural origins, taxonomic classification, mitigation pathways, and the oracle audit framework for algorithmic bias in large language models

Neto, A. B. D. O. (2026) · Derecho y cambio social. · doi:10.54899/dcs.v23i91.5915

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision–Language Models

Chowdhury, R., Rupprecht, T., Shen, X., Zhao, P., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37429-5_6

InDe-LLM: Defending against Jailbreak Attacks in LLM-Powered Systems via Intention Disentangling

Wang, Y., Zhang, Q., Zhou, C., Go, G., Shi, D., & Jiang, Y. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3797136

Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification

Gu, Z., Zhang, T., Zhang, X., Wang, Z., Zhang, H., Wei, Y., Lu, J., Ma, T., Zhang, X., Zhang, H., et al. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.1502 · Cited by 1

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models

Weng, Z., Zhang, J., Cai, K., Li, Y., Wang, P., & Tian, Y. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.852

PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models

Zheng, H., Zhu, Y., Yuan, Y., Yuan, B., Zhang, W., Tang, S., & Xiao, J. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.236

SteerForce at SemEval-2026 Task 11: Reducing Content Effects Using Layered Activation Steering

Tratzsch, N., Al-Raian, A., Marreddy, M., & Mehler, A. (2026) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/2026.semeval-1.143

How Models Say No: Localizing Safety Mechanisms in Mixture-of-Experts Models

Lanquillon, C., & Schacht, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30860-3_6

Agentic Taxation Optimization via LLM SMT-Constraint Reasoning

Hwang, T.-C., Yu, F., & Jiang, J.-H. R. (2026) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1145/3786583.3786917

Personalized Text Generation with Contrastive Activation Steering

Zhang, J., Liu, Y., Wang, W., Liu, Q., Wu, S., Wang, L., & Chua, T. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.353 · Cited by 5

Contrastive Covariance Subspaces for Activation SteeringPreprint

Xenos, A., Plitsis, M., Foteinopoulou, N., Panagakis, Y., & Patras, I. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.14025

Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation AdditionPreprint

Baroudi, S., Labrak, Y., Melucci, P., Burdisso, S., Motlíček, P., Bredin, H., Ravanelli, M., & Marxer, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.04683

Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering

Cheng, Z., Wang, Z. J., Fu, Y., Jiang, Z., Yin, Y., Wang, C., & Gu, Q. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.174 · Cited by 4

Scaling laws for activation steering with Llama 2 models and refusal mechanismsPreprint

Ali, S. A. R., Xu, J., Yang, I., Li, J. X., Arslan, A., & Benham, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.11771 · Cited by 2