English
Related papers

Related papers: Sparse Interventions in Language Models with Diffe…

200 papers

Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded in the internal…

Computation and Language · Computer Science 2025-09-18 Zhuoxuan Zhang , Jinhao Duan , Edward Kim , Kaidi Xu

Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked…

Computation and Language · Computer Science 2026-03-03 Litian Liu , Reza Pourreza , Sunny Panchal , Apratim Bhattacharyya , Yubing Jian , Yao Qin , Roland Memisevic

Despite widespread success in language understanding and generation, large language models (LLMs) exhibit unclear and often inconsistent behavior when faced with tasks that require probabilistic reasoning. In this work, we present the first…

Computation and Language · Computer Science 2025-09-29 Mobina Pournemat , Keivan Rezaei , Gaurang Sriramanan , Arman Zarei , Jiaxiang Fu , Yang Wang , Hamid Eghbalzadeh , Soheil Feizi

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Despite the recent successes of large, pretrained neural language models (LLMs), comparatively little is known about the representations of linguistic structure they learn during pretraining, which can lead to unexpected behaviors in…

Computation and Language · Computer Science 2024-12-24 Adam Davies , Jize Jiang , ChengXiang Zhai

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Machine Learning · Computer Science 2025-08-07 Gonçalo Paulo , Alex Mallen , Caden Juang , Nora Belrose

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Computation and Language · Computer Science 2026-04-21 Nils Feldhus , Laura Kopf

For Pretrained Language Models (PLMs), their susceptibility to noise has recently been linked to subword segmentation. However, it is unclear which aspects of segmentation affect their understanding. This study assesses the robustness of…

Computation and Language · Computer Science 2024-10-15 Xinzhe Li , Ming Liu , Shang Gao

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…

Computation and Language · Computer Science 2024-01-30 Iñigo Parra

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Computation and Language · Computer Science 2025-09-29 Zheng Wei Lim , Alham Fikri Aji , Trevor Cohn

Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-10 Yizhou Lu , Mingkun Huang , Xinghua Qu , Pengfei Wei , Zejun Ma

Attribution methods assess the contribution of inputs to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the prediction. Though conceptually simple,…

Computation and Language · Computer Science 2021-03-03 Nicola De Cao , Michael Schlichtkrull , Wilker Aziz , Ivan Titov

Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…

Artificial Intelligence · Computer Science 2026-05-14 Shiguang Wu , Yaqing Wang , Quanming Yao

In recent literature, contextual pretrained Language Models (LMs) demonstrated their potential in generalizing the knowledge to several Natural Language Processing (NLP) tasks including supervised Word Sense Disambiguation (WSD), a…

Computation and Language · Computer Science 2019-11-18 Max Raphael Sobroza , Tales Marra , Deok-Hee Kim-Dufor , Claude Berrou

Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their application in high-risk domains. Current hallucination detection…

Computation and Language · Computer Science 2025-12-25 Shize Liang , Hongzhi Wang

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts…

Computation and Language · Computer Science 2026-03-23 Weiyao Luo , Suncong Zheng , Heming Xia , Weikang Wang , Yan Lei , Tianyu Liu , Shuang Chen , Zhifang Sui

Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…

Computation and Language · Computer Science 2024-11-06 E. Zhixuan Zeng , Yuhao Chen , Alexander Wong

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Na Min An , Yoonna Jang , Yusuke Hirota , Ryo Hachiuma , Isabelle Augenstein , Hyunjung Shim

Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations in LMs remains an unsolved problem, in part due to a dilemma…

Computation and Language · Computer Science 2026-03-26 Joshua Rozner , Cory Shain

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple,…

Computation and Language · Computer Science 2026-04-01 Zoë Prins , Samuele Punzo , Frank Wildenburg , Giovanni Cinà , Sandro Pezzelle