English
Related papers

Related papers: Finding the Translation Switch: Discovering and Ex…

200 papers

Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage, but suffer from hallucinations where they choose incorrect tools, provide malformed parameters and exhibit 'tool bypass' behavior by performing…

Artificial Intelligence · Computer Science 2026-01-09 Kait Healy , Bharathi Srinivasan , Visakh Madathil , Jing Wu

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for…

Computation and Language · Computer Science 2025-03-06 Samir Abdaljalil , Filippo Pallucchini , Andrea Seveso , Hasan Kurban , Fabio Mercorio , Erchin Serpedin

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised…

Computation and Language · Computer Science 2026-04-29 Baban Gain , Dibyanayan Bandyopadhyay , Asif Ekbal , Trilok Nath Singh

Translation-tailored Large language models (LLMs) exhibit remarkable translation capabilities, even competing with supervised-trained commercial translation systems. However, off-target translation remains an unsolved problem, especially…

Computation and Language · Computer Science 2024-03-22 Changtong Zan , Liang Ding , Li Shen , Yibing Zhen , Weifeng Liu , Dacheng Tao

Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…

Computation and Language · Computer Science 2025-07-18 Xinyu Tang , Zhihao Lv , Xiaoxue Cheng , Junyi Li , Wayne Xin Zhao , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Kaichen Zhang , Yifei Shen , Bo Li , Ziwei Liu

This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. We design the…

Computation and Language · Computer Science 2024-06-07 Xu Huang , Zhirui Zhang , Xiang Geng , Yichao Du , Jiajun Chen , Shujian Huang

Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable…

Computation and Language · Computer Science 2024-04-12 Rahul Mehta , Andrew Hoblitzell , Jack O'Keefe , Hyeju Jang , Vasudeva Varma

Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such…

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

Understanding and interpreting the internal representations of large language models (LLMs) remains an open challenge. Patchscopes introduced a method for probing internal activations by patching them into new prompts, prompting models to…

Computation and Language · Computer Science 2025-03-11 Jonathan Jacobi , Gal Niv

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Software Engineering · Computer Science 2025-10-06 Kriz Tahimic , Charibeth Cheng

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…

Computation and Language · Computer Science 2025-05-26 Jannik Brinkmann , Chris Wendler , Christian Bartelt , Aaron Mueller

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Computation and Language · Computer Science 2026-05-05 Or Shafran , Atticus Geiger , Mor Geva

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Machine Learning · Computer Science 2025-07-14 Gonçalo Paulo , Nora Belrose

Large Language Models (LLMs) exhibit In-Context Learning (ICL), which enables the model to perform new tasks conditioning only on the examples provided in the context without updating the model's weights. While ICL offers fast adaptation…

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Large language models (LLMs) have demonstrated human-like abilities in language-based tasks. While language is a defining feature of human intelligence, it emerges from more fundamental neurophysical processes rather than constituting the…

Neurons and Cognition · Quantitative Biology 2025-09-12 Doai Ngo , Mingxuan Sun , Zhengji Zhang , Ashwin G Ramayya , Mark Schnitzer , Zhe Zhao