English
Related papers

Related papers: Exploring Task Performance with Interpretable Mode…

200 papers

Resolving semantic ambiguity has long been recognised as a central challenge in the field of Machine Translation. Recent work on benchmarking translation performance on ambiguous sentences has exposed the limitations of conventional Neural…

Computation and Language · Computer Science 2023-10-24 Vivek Iyer , Pinzhen Chen , Alexandra Birch

Large language models have become extremely popular recently due to their ability to achieve strong performance on a variety of tasks, such as text generation and rewriting, but their size and computation cost make them difficult to access,…

Computation and Language · Computer Science 2026-01-08 Anthony Lamelas

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Machine Learning · Computer Science 2024-11-08 Jacob Dunefsky , Philippe Chlenski , Neel Nanda

While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different…

Computation and Language · Computer Science 2023-02-01 Daking Rai , Yilun Zhou , Bailin Wang , Ziyu Yao

Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank…

Computation and Language · Computer Science 2025-10-31 Zeliang Zong , Kai Zhang , Zheyang Li , Wenming Tan , Ye Ren , Yiyan Zhai , Jilin Hu

In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learning abilities continue to improve, understanding this…

Machine Learning · Computer Science 2024-10-03 Can Demircan , Tankred Saanum , Akshay K. Jagadish , Marcel Binz , Eric Schulz

Despite strong performance in audio perception tasks, large audio-language models (AudioLLMs) remain opaque to interpretation. A major factor behind this lack of interpretability is that individual neurons in these models frequently…

Sound · Computer Science 2026-02-27 Townim Faisal Chowdhury , Ta Duc Huy , Siqi Pan , Jeremy Stoddard , Zhibin Liao

The rapid growth of large language models (LLMs) presents significant deployment challenges due to their massive computational and memory demands. While model compression, such as network pruning, offers potential solutions, most existing…

Machine Learning · Computer Science 2026-04-07 Ziwei Li , Yuang Ma , Yi Kang

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

In this paper, we study whether an off-the-shelf LLM can be adapted into a discrete, variable-length token compressor and decompressor for long-context processing. To this end, we design a self-expressive autoencoding framework that…

Computation and Language · Computer Science 2026-05-14 Wenbing Li , Yiran Wang , Zikai Song , Jielei Zhang , Tianhao Zhao , Junkai Lin , Wei Yang

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard…

Computation and Language · Computer Science 2023-10-16 Eldar Kurtic , Denis Kuznedelev , Elias Frantar , Michael Goin , Dan Alistarh

Large language models (LLMs) demonstrate outstanding performance in various tasks in machine learning and have thus become one of the most important workloads in today's computing landscape. However, deploying LLM inference poses challenges…

Machine Learning · Computer Science 2024-06-21 Jungi Lee , Wonbeom Lee , Jaewoong Sim

Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances,…

Computation and Language · Computer Science 2025-10-28 Chenheng Zhang , Tianqi Du , Jizhe Zhang , Mingqing Xiao , Yifei Wang , Yisen Wang , Zhouchen Lin

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task.…

Computation and Language · Computer Science 2022-12-06 Lunyiu Nie , Jiuding Sun , Yanlin Wang , Lun Du , Lei Hou , Juanzi Li , Shi Han , Dongmei Zhang , Jidong Zhai

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks by understanding input information and predicting corresponding outputs. However, the internal mechanisms by which LLMs comprehend input and…

Computation and Language · Computer Science 2025-01-07 Zhou Yang , Zhengyu Qi , Zhaochun Ren , Zhikai Jia , Haizhou Sun , Xiaofei Zhu , Xiangwen Liao

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Computation and Language · Computer Science 2026-04-16 Corentin Kervadec , Iuliia Lysova , Marco Baroni , Gemma Boleda

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

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…

Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…

Computation and Language · Computer Science 2026-05-25 Dongxin Guo , Jikun Wu , Siu Ming Yiu

This paper investigates the ability of large language models (LLMs) to recognise and solve tasks which have been obfuscated beyond recognition. Focusing on competitive programming and benchmark tasks (LeetCode and MATH), we compare…

Machine Learning · Computer Science 2025-05-30 Radzim Sendyka , Christian Cabrera , Andrei Paleyes , Diana Robinson , Neil Lawrence