English
Related papers

Related papers: Sparse Interventions in Language Models with Diffe…

200 papers

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

Computation and Language · Computer Science 2024-08-01 Charles Jin , Martin Rinard

Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user's intent of producing natural language at inference time, however only one word will minimize the task's loss function at…

Computation and Language · Computer Science 2024-02-23 Emily McMilin

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

Computation and Language · Computer Science 2025-09-16 Yi Jing , Zijun Yao , Hongzhu Guo , Lingxu Ran , Xiaozhi Wang , Lei Hou , Juanzi Li

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Computers and Society · Computer Science 2025-06-11 Bryan Chen Zhengyu Tan , Roy Ka-Wei Lee

Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs…

Computation and Language · Computer Science 2024-06-07 Tianyi Tang , Wenyang Luo , Haoyang Huang , Dongdong Zhang , Xiaolei Wang , Xin Zhao , Furu Wei , Ji-Rong Wen

Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring…

Computation and Language · Computer Science 2016-08-25 Thomas Kober , Julie Weeds , Jeremy Reffin , David Weir

Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate…

Computation and Language · Computer Science 2024-10-16 Deniz Bayazit , Negar Foroutan , Zeming Chen , Gail Weiss , Antoine Bosselut

Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this…

Machine Learning · Computer Science 2026-05-22 Haotian Xu , Jiannan Yang , Tian Gao , Tsui-Wei Weng , Tengfei Ma

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Computation and Language · Computer Science 2022-08-30 Boyang Xue , Shoukang Hu , Junhao Xu , Mengzhe Geng , Xunying Liu , Helen Meng

Debiasing language models from unwanted behaviors in Natural Language Understanding tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and…

Computation and Language · Computer Science 2022-12-06 Johannes Mario Meissner , Saku Sugawara , Akiko Aizawa

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

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that…

Machine Learning · Computer Science 2026-01-28 Claire O'Brien , Jessica Seto , Dristi Roy , Aditya Dwivedi , Sunishchal Dev , Kevin Zhu , Sean O'Brien , Ashwinee Panda , Ryan Lagasse

Understanding the internal representations of large language models (LLMs) can help explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose…

Computation and Language · Computer Science 2024-06-10 Asma Ghandeharioun , Avi Caciularu , Adam Pearce , Lucas Dixon , Mor Geva

Differential framing of issues can lead to divergent world views on important issues. This is especially true in domains where the information presented can reach a large audience, such as traditional and social media. Scalable and reliable…

Computation and Language · Computer Science 2023-02-08 Xiaobo Guo , Weicheng Ma , Soroush Vosoughi

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Computation and Language · Computer Science 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We systematically analyze both encoder and decoder based LLMs…

Machine Learning · Computer Science 2026-04-13 Muhammad Umair Haider , Hammad Rizwan , Hassan Sajjad , Peizhong Ju , A. B. Siddique

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…

Computation and Language · Computer Science 2025-01-07 Libing Yuan , Shuaibo Hu , Kui Yu , Le Wu

Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken…

Computation and Language · Computer Science 2020-11-04 Mahdi Namazifar , Gokhan Tur , Dilek Hakkani Tür

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

Computation and Language · Computer Science 2024-02-14 Xinyi Wang , Wanrong Zhu , Michael Saxon , Mark Steyvers , William Yang Wang