English
Related papers

Related papers: Depth-Wise Activation Steering for Honest Language…

200 papers

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…

Machine Learning · Computer Science 2025-02-06 Nicholas Goldowsky-Dill , Bilal Chughtai , Stefan Heimersheim , Marius Hobbhahn

Difficult problems, which often result in long reasoning traces, are widely recognized as key factors for enhancing the performance of reasoning models. However, such high-challenge problems are scarce, limiting the size of available…

Computation and Language · Computer Science 2025-03-25 Si Shen , Fei Huang , Zhixiao Zhao , Chang Liu , Tiansheng Zheng , Danhao Zhu

Learning from demonstration (LfD) is an intuitive framework allowing non-expert users to easily (re-)program robots. However, the quality and quantity of demonstrations have a great influence on the generalization performances of LfD…

Robotics · Computer Science 2020-08-07 Hakan Girgin , Emmanuel Pignat , Noémie Jaquier , Sylvain Calinon

Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B)…

Machine Learning · Computer Science 2026-03-05 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Sophisticated instrumentation for AI systems might have indicators that signal misalignment from human values, not unlike a "check engine" light in cars. One such indicator of misalignment is deceptiveness in generated responses. Future AI…

Artificial Intelligence · Computer Science 2025-09-18 Gerard Boxo , Ryan Socha , Daniel Yoo , Shivam Raval

Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. We propose explanation-based…

Computation and Language · Computer Science 2023-06-07 Josh Magnus Ludan , Yixuan Meng , Tai Nguyen , Saurabh Shah , Qing Lyu , Marianna Apidianaki , Chris Callison-Burch

Effective safety auditing of large language models (LLMs) demands tools that go beyond black-box probing and systematically uncover vulnerabilities rooted in model internals. We present a comprehensive, interpretability-driven jailbreaking…

Cryptography and Security · Computer Science 2026-04-24 Krishiv Agarwal , Ramneet Kaur , Colin Samplawski , Manoj Acharya , Anirban Roy , Daniel Elenius , Brian Matejek , Adam D. Cobb , Susmit Jha

Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbose, even for simple problems, leading to wasted context,…

Artificial Intelligence · Computer Science 2025-07-09 Seyedarmin Azizi , Erfan Baghaei Potraghloo , Massoud Pedram

Bridging the significant gap between large language model's English and non-English performance presents a great challenge. While some previous studies attempt to mitigate this gap with translated training data, the recently proposed…

Computation and Language · Computer Science 2024-11-07 Wenhao Zhu , Shujian Huang , Fei Yuan , Cheng Chen , Jiajun Chen , Alexandra Birch

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

Artificial Intelligence · Computer Science 2025-10-17 Vincent Siu , Nicholas Crispino , David Park , Nathan W. Henry , Zhun Wang , Yang Liu , Dawn Song , Chenguang Wang

Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…

Machine Learning · Computer Science 2026-03-13 Eric Bigelow , Daniel Wurgaft , YingQiao Wang , Noah Goodman , Tomer Ullman , Hidenori Tanaka , Ekdeep Singh Lubana

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…

Computation and Language · Computer Science 2024-09-02 Li Du , Zhouhao Sun , Xiao Ding , Yixuan Ma , Yang Zhao , Kaitao Qiu , Ting Liu , Bing Qin

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

The test bench time needed for model-based calibration can be reduced with active learning methods for test design. This paper presents an improved strategy for active output selection. This is the task of learning multiple models in the…

Machine Learning · Computer Science 2021-01-12 Adrian Prochaska , Julien Pillas , Bernard Bäker

We introduce a new approach in which several advanced large language models-specifically GPT-4-0125-preview, Meta-LLAMA-3-70B-Instruct, Claude-3-Opus, and Gemini-1.5-Flash-collaborate to both produce and answer intricate, doctoral-level…

Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than…

Artificial Intelligence · Computer Science 2026-03-19 Ai Jian , Xiaoyun Zhang , Wanrou Du , Jingqing Ruan , Jiangbo Pei , Weipeng Zhang , Ke Zeng , Xunliang Cai

Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model…

Computation and Language · Computer Science 2024-06-25 Asa Cooper Stickland , Alexander Lyzhov , Jacob Pfau , Salsabila Mahdi , Samuel R. Bowman

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Software Engineering · Computer Science 2025-07-24 Emir Bosnak , Sahand Moslemi , Mayasah Lami , Anil Koyuncu

Routing is widely used to scale large language models, from Mixture-of-Experts gating to multi-model/tool selection. A common belief is that routing to a task ``expert'' activates sparser internal computation and thus yields more certain…

Artificial Intelligence · Computer Science 2026-04-01 Dianxing Zhang , Gang Li , Sheng Li