English
Related papers

Related papers: How Does Controllability Emerge In Language Models…

200 papers

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the…

Steering vectors are a promising approach to aligning language model behavior at inference time. In this paper, we propose a framework to assess the limitations of steering vectors as alignment mechanisms. Using a framework of transformer…

Computation and Language · Computer Science 2025-05-05 Chebrolu Niranjan , Kokil Jaidka , Gerard Christopher Yeo

The iterated learning model is an agent model which simulates the transmission of of language from generation to generation. It is used to study how the language adapts to pressures imposed by transmission. In each iteration, a language…

Computation and Language · Computer Science 2024-11-28 Jack Bunyan , Seth Bullock , Conor Houghton

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

We present a training-free framework for continuous and controllable image editing at test time for text-conditioned generative models. In contrast to prior approaches that rely on additional training or manual user intervention, we find…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Yigit Ekin , Yossi Gandelsman

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…

Computation and Language · Computer Science 2025-10-30 Chunyuan Deng , Ruidi Chang , Hanjie Chen

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped potential of…

Computation and Language · Computer Science 2024-09-04 Chen Qian , Jie Zhang , Wei Yao , Dongrui Liu , Zhenfei Yin , Yu Qiao , Yong Liu , Jing Shao

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Computation and Language · Computer Science 2026-03-17 Amr Hegazy , Mostafa Elhoushi , Amr Alanwar

Pretraining data has a direct impact on the behaviors and quality of language models (LMs), but we only understand the most basic principles of this relationship. While most work focuses on pretraining data's effect on downstream task…

Computation and Language · Computer Science 2025-04-18 Jack Merullo , Noah A. Smith , Sarah Wiegreffe , Yanai Elazar

The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, there does not exist a mechanism…

Artificial Intelligence · Computer Science 2022-03-03 Jiabao Ji , Yoon Kim , James Glass , Tianxing He

Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety evaluations as if the model cannot detect the intervention. We test this assumption, introducing steering awareness: a…

Computation and Language · Computer Science 2026-03-20 Joshua Fonseca Rivera , David Demitri Africa

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Computation and Language · Computer Science 2023-05-04 Ruochen Zhao , Shafiq Joty , Yongjie Wang , Tan Wang

From school playgrounds to corporate boardrooms, status hierarchies -- rank orderings based on respect and perceived competence -- are universal features of human social organization. Language models trained on human-generated text…

Human-Computer Interaction · Computer Science 2026-01-27 Emilio Barkett

Stance detection has emerged as a popular task in natural language processing research, enabled largely by the abundance of target-specific social media data. While there has been considerable research on the development of stance detection…

Computation and Language · Computer Science 2025-02-05 Prasanta Bhattacharya , Hong Zhang , Yiming Cao , Wei Gao , Brandon Siyuan Loh , Joseph J. P. Simons , Liang Ze Wong

Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work, our goal is to propose a simple yet effective solution to…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Gabriela Csurka , Tyler L. Hayes , Diane Larlus , Riccardo Volpi

Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks. However, few works research robustness and explainability issues of their evaluation…

Computation and Language · Computer Science 2022-10-31 Maria Lymperaiou , George Manoliadis , Orfeas Menis Mastromichalakis , Edmund G. Dervakos , Giorgos Stamou

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for each block in a frozen pretrained model, making it possible…

Machine Learning · Computer Science 2025-11-12 Nora Belrose , Igor Ostrovsky , Lev McKinney , Zach Furman , Logan Smith , Danny Halawi , Stella Biderman , Jacob Steinhardt

Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations…

Computation and Language · Computer Science 2024-08-14 Asma Ghandeharioun , Ann Yuan , Marius Guerard , Emily Reif , Michael A. Lepori , Lucas Dixon

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Computation and Language · Computer Science 2026-02-11 Bakhtawar Ahtisham , Kirk Vanacore , Zhuqian Zhou , Jinsook Lee , Rene F. Kizilcec

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho
‹ Prev 1 8 9 10 Next ›