English
Related papers

Related papers: Sparse Autoencoders Reveal Temporal Difference Lea…

200 papers

Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various domains that affect the public at large, such as industry, academia, finance, health. While…

Computation and Language · Computer Science 2026-05-13 Dan Pluth , Zachary Nicholas Houghton , Yu Zhou , Vijay K. Gurbani

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Computation and Language · Computer Science 2026-02-10 Roy Xie , Junlin Wang , Paul Rosu , Chunyuan Deng , Bolun Sun , Zihao Lin , Bhuwan Dhingra

Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, their generalization is inconsistent: while these models can perform impressively in some settings, fine-tuned…

Robotics · Computer Science 2026-03-20 Aiden Swann , Lachlain McGranahan , Hugo Buurmeijer , Monroe Kennedy , Mac Schwager

Assessing student's answers and in particular natural language answers is a crucial challenge in the field of education. Advances in machine learning, including transformer-based models such as Large Language Models(LLMs), have led to…

Computers and Society · Computer Science 2024-01-12 Priti Oli , Rabin Banjade , Jeevan Chapagain , Vasile Rus

Low-Rank Adaptation (LoRA) has emerged as a widely adopted approach for adapting large language models, yet the internal representational changes induced by LoRA fine-tuning remain insufficiently understood. In this work, we investigate the…

Machine Learning · Computer Science 2026-05-29 Prasanth K K

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to…

Computation and Language · Computer Science 2024-04-18 Mert Yuksekgonul , Varun Chandrasekaran , Erik Jones , Suriya Gunasekar , Ranjita Naik , Hamid Palangi , Ece Kamar , Besmira Nushi

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered:…

Machine Learning · Computer Science 2025-10-07 Xu Wang , Yan Hu , Benyou Wang , Difan Zou

Temporal expression (TE) normalization is a well-studied problem. However, the predominately used rule-based systems are highly restricted to specific settings, and upcoming machine learning approaches suffer from a lack of labeled data. In…

Computation and Language · Computer Science 2024-04-12 Akash Kumar Gautam , Lukas Lange , Jannik Strötgen

Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL). However, such methods require extensive data and compute, making them impractical under many realistic training budgets.…

Machine Learning · Computer Science 2026-04-17 Dai Do , Manh Nguyen , Svetha Venkatesh , Hung Le

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

Computation and Language · Computer Science 2024-04-12 Linyi Yang , Shuibai Zhang , Zhuohao Yu , Guangsheng Bao , Yidong Wang , Jindong Wang , Ruochen Xu , Wei Ye , Xing Xie , Weizhu Chen , Yue Zhang

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

Large Language Models (LLMs) frequently exhibit strong translation abilities, even without task-specific fine-tuning. However, the internal mechanisms governing this innate capability remain largely opaque. To demystify this process, we…

Computation and Language · Computer Science 2026-01-19 Xinwei Wu , Heng Liu , Xiaohu Zhao , Yuqi Ren , Linlong Xu , Longyue Wang , Deyi Xiong , Weihua Luo , Kaifu Zhang

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Machine Learning · Computer Science 2025-10-13 T. Ed Li , Junyu Ren

Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Desh Raj , Gil Keren , Junteng Jia , Jay Mahadeokar , Ozlem Kalinli

Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is limited by the requirement for contrastive datasets or large…

Computation and Language · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

While LLMs have revolutionized the field of machine learning due to their high performance on a strikingly wide range of problems, they are also known to hallucinate false answers and underperform on less canonical versions of the same…

Machine Learning · Computer Science 2025-09-11 Kavi Gupta , Kate Sanders , Armando Solar-Lezama

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential. A standard serving practice concatenates the full dialogue history at every turn,…

Computation and Language · Computer Science 2026-05-13 Xueqi Cheng , Qiong Wu , Zhengyi Zhou , Xugui Zhou , Tyler Derr , Yushun Dong