English
Related papers

Related papers: Separating Tongue from Thought: Activation Patchin…

200 papers

Entity tracking (ET), the ability to keep track of states, is a fundamental skill that underlies complex reasoning. An increasing amount of work investigates how transformer language models (LMs) solve entity binding $\textit{without}$…

Computation and Language · Computer Science 2026-05-29 Zilu Tang , Qiao Zhao , Gabriel Franco , Derry Wijaya , Aaron Mueller , Sebastian Schuster , Najoung Kim

Large language models (LLMs) demonstrate remarkable machine translation (MT) abilities via prompting, even though they were not explicitly trained for this task. However, even given the incredible quantities of data they are trained on,…

Computation and Language · Computer Science 2023-02-16 Marjan Ghazvininejad , Hila Gonen , Luke Zettlemoyer

Large language models (LLMs) have learned vast amounts of factual knowledge through self-supervised pre-training on large-scale corpora. Meanwhile, LLMs have also demonstrated excellent multilingual capabilities, which can express the…

Computation and Language · Computer Science 2024-11-27 Pengfei Cao , Yuheng Chen , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao

While pretrained language models (PLMs) primarily serve as general-purpose text encoders that can be fine-tuned for a wide variety of downstream tasks, recent work has shown that they can also be rewired to produce high-quality word…

Computation and Language · Computer Science 2023-05-30 Tommaso Green , Simone Paolo Ponzetto , Goran Glavaš

Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic…

Computation and Language · Computer Science 2019-04-29 Nelson F. Liu , Matt Gardner , Yonatan Belinkov , Matthew E. Peters , Noah A. Smith

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Machine Learning · Computer Science 2023-11-02 Fabien Roger , Ryan Greenblatt

Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human…

Computation and Language · Computer Science 2025-12-12 Weixiang Zhao , Jiahe Guo , Yang Deng , Tongtong Wu , Wenxuan Zhang , Yulin Hu , Xingyu Sui , Yanyan Zhao , Wanxiang Che , Bing Qin , Tat-Seng Chua , Ting Liu

Large language models (LLMs) demonstrate remarkable ability in cross-lingual tasks. Understanding how LLMs acquire this ability is crucial for their interpretability. To quantify the cross-lingual ability of LLMs accurately, we propose a…

Computation and Language · Computer Science 2025-05-23 Kaiyu He , Tong Zhou , Yubo Chen , Delai Qiu , Shengping Liu , Kang Liu , Jun Zhao

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Computation and Language · Computer Science 2025-04-14 Miguel López-Otal , Jorge Gracia , Jordi Bernad , Carlos Bobed , Lucía Pitarch-Ballesteros , Emma Anglés-Herrero

Language models demonstrate remarkable capacity to generalize representations learned in one modality to downstream tasks in other modalities. Can we trace this ability to individual neurons? We study the case where a frozen text…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Sarah Schwettmann , Neil Chowdhury , Samuel Klein , David Bau , Antonio Torralba

Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning…

Computation and Language · Computer Science 2025-10-16 A. Bochkov

While state-of-the-art language models (LMs) surpass the vast majority of humans in certain domains, their reasoning remains largely opaque, undermining trust in their output. Furthermore, while autoregressive LMs can output explicit…

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

This paper introduces the idea of applying signal processing inside a Large Language Model (LLM). With the recent explosion of generative AI, our work can help bridge two fields together, namely the field of signal processing and large…

Computation and Language · Computer Science 2024-09-19 Prateek Verma , Mert Pilanci

In neural network models of language, words are commonly represented using context-invariant representations (word embeddings) which are then put in context in the hidden layers. Since words are often ambiguous, representing the…

Computation and Language · Computer Science 2019-06-13 Laura Aina , Kristina Gulordava , Gemma Boleda

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

Large language models (LLMs) like GPT are often conceptualized as passive predictors, simulators, or even stochastic parrots. We instead conceptualize LLMs by drawing on the theory of active inference originating in cognitive science and…

Computation and Language · Computer Science 2023-11-20 Jan Kulveit , Clem von Stengel , Roman Leventov

The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs, is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that…

Computation and Language · Computer Science 2022-08-12 Myeongjun Jang , Frank Mtumbuka , Thomas Lukasiewicz

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

Computation and Language · Computer Science 2017-11-23 Dinghan Shen , Yizhe Zhang , Ricardo Henao , Qinliang Su , Lawrence Carin

Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications. To…

Computation and Language · Computer Science 2023-07-06 Jin Myung Kwak , Minseon Kim , Sung Ju Hwang