English
Related papers

Related papers: How Does Controllability Emerge In Language Models…

200 papers

With the growing complexity and capability of large language models, a need to understand model reasoning has emerged, often motivated by an underlying goal of controlling and aligning models. While numerous interpretability and steering…

Machine Learning · Computer Science 2025-02-12 Usha Bhalla , Suraj Srinivas , Asma Ghandeharioun , Himabindu Lakkaraju

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Computation and Language · Computer Science 2026-02-23 Joschka Braun

Concept guidance has emerged as a cheap and simple way to control the behavior of language models by probing their hidden representations for concept vectors and using them to perturb activations at inference time. While the focus of…

Computation and Language · Computer Science 2024-02-23 Dimitri von Rütte , Sotiris Anagnostidis , Gregor Bachmann , Thomas Hofmann

Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either…

Computation and Language · Computer Science 2025-10-16 Arthur Vogels , Benjamin Wong , Yann Choho , Annabelle Blangero , Milan Bhan

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…

Computation and Language · Computer Science 2022-05-12 Nishant Subramani , Nivedita Suresh , Matthew E. Peters

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Computation and Language · Computer Science 2026-03-04 Chung-En Sun , Ge Yan , Zimo Wang , Tsui-Wei Weng

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

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

Interventions in language models (LMs) are applied strategically to steer model behavior during the forward pass. Learnable interventions, also known as representation fine-tuning, aim to apply pointwise control within the concept subspace…

Computation and Language · Computer Science 2025-06-10 Chunyuan Deng , Ruidi Chang , Hanjie Chen

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…

Applications · Statistics 2026-05-14 Luxu Liang , Xiang Li

Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model…

Computation and Language · Computer Science 2025-05-30 Daniel Beaglehole , Adityanarayanan Radhakrishnan , Enric Boix-Adserà , Mikhail Belkin

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of…

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Computation and Language · Computer Science 2025-04-15 Alessandro Stolfo , Vidhisha Balachandran , Safoora Yousefi , Eric Horvitz , Besmira Nushi

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Machine Learning · Computer Science 2025-05-22 Tong Wu , Chong Xiang , Jiachen T. Wang , G. Edward Suh , Prateek Mittal

The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…

Machine Learning · Computer Science 2025-10-08 Damjan Kalajdzievski

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Artificial Intelligence · Computer Science 2025-08-13 Shivam Dubey

When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…

Computation and Language · Computer Science 2025-11-07 Amir Zur , Atticus Geiger , Ekdeep Singh Lubana , Eric Bigelow

Modern generative models demonstrate impressive capabilities, likely stemming from an ability to identify and manipulate abstract concepts underlying their training data. However, fundamental questions remain: what determines the concepts a…

Machine Learning · Computer Science 2024-12-12 Core Francisco Park , Maya Okawa , Andrew Lee , Hidenori Tanaka , Ekdeep Singh Lubana
‹ Prev 1 2 3 10 Next ›