English
Related papers

Related papers: LM-Debugger: An Interactive Tool for Inspection an…

200 papers

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on the quality of LM…

Computation and Language · Computer Science 2024-06-11 Lucas Weber , Jaap Jumelet , Elia Bruni , Dieuwke Hupkes

Large Language Models (LLMs) such as ChatGPT and Llama have become prevalent in real-world applications, exhibiting impressive text generation performance. LLMs are fundamentally developed from a scenario where the input data remains static…

Artificial Intelligence · Computer Science 2024-09-09 Cheng'an Wei , Yue Zhao , Yujia Gong , Kai Chen , Lu Xiang , Shenchen Zhu

Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have been studied…

Computation and Language · Computer Science 2024-10-24 Clement Neo , Shay B. Cohen , Fazl Barez

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Computation and Language · Computer Science 2025-06-09 Bhavik Chandna , Zubair Bashir , Procheta Sen

Large Language Models (LLMs) have become dominant in the Natural Language Processing (NLP) field causing a huge surge in progress in a short amount of time. However, their limitations are still a mystery and have primarily been explored…

Software Engineering · Computer Science 2024-04-11 Nathan Cooper , Torsten Scholak

High-dimensional data remains a pervasive challenge in machine learning, often undermining model interpretability and computational efficiency. While Large Language Models (LLMs) have shown promise for dimensionality reduction through…

Machine Learning · Computer Science 2025-10-08 Mohamed Bal-Ghaoui , Fayssal Sabri

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for each block in a frozen pretrained model, making it possible…

Machine Learning · Computer Science 2025-11-12 Nora Belrose , Igor Ostrovsky , Lev McKinney , Zach Furman , Logan Smith , Danny Halawi , Stella Biderman , Jacob Steinhardt

Large Language Models (LLMs) can generate plausible test code. Intuitively they generate this by imitating tests seen in their training data, rather than reasoning about execution semantics. However, such reasoning is important when…

Software Engineering · Computer Science 2025-03-12 Philipp Straubinger , Marvin Kreis , Stephan Lukasczyk , Gordon Fraser

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable…

Computation and Language · Computer Science 2024-02-06 Chandan Singh , Jeevana Priya Inala , Michel Galley , Rich Caruana , Jianfeng Gao

This paper introduces LogitLens4LLMs, a toolkit that extends the Logit Lens technique to modern large language models. While Logit Lens has been a crucial method for understanding internal representations of language models, it was…

Computation and Language · Computer Science 2025-03-18 Zhenyu Wang

Social media influence campaigns pose significant challenges to public discourse and democracy. Traditional detection methods fall short due to the complexity and dynamic nature of social media. Addressing this, we propose a novel detection…

Social and Information Networks · Computer Science 2023-11-15 Luca Luceri , Eric Boniardi , Emilio Ferrara

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…

Computation and Language · Computer Science 2024-06-18 Yi Yang , Hanyu Duan , Ahmed Abbasi , John P. Lalor , Kar Yan Tam

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

Computation and Language · Computer Science 2026-05-04 Gaofei Shen , Martijn Bentum , Tom Lentz , Afra Alishahi , Grzegorz Chrupała

Large Language Models (LLMs) have demonstrated impressive performance in various NLP tasks, but they still suffer from challenges such as hallucination and weak numerical reasoning. To overcome these challenges, external tools can be used…

Computation and Language · Computer Science 2023-06-26 Yuchen Zhuang , Yue Yu , Kuan Wang , Haotian Sun , Chao Zhang

Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files, run code, call APIs, etc. Further, modern reasoning-based…

Programming Languages · Computer Science 2025-12-19 Daniel Nichols , Prajwal Singhania , Charles Jekel , Abhinav Bhatele , Harshitha Menon

To learn about real world phenomena, scientists have traditionally used models with clearly interpretable elements. However, modern machine learning (ML) models, while powerful predictors, lack this direct elementwise interpretability (e.g.…

Machine Learning · Statistics 2024-07-16 Timo Freiesleben , Gunnar König , Christoph Molnar , Alvaro Tejero-Cantero

Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on surface-level lexical or stylistic cues, treating dialogue as a flat sequence of tokens and…

Computation and Language · Computer Science 2026-04-28 Jisoo Yang , Jongwon Ryu , Minuk Ma , Trung X. Pham , Junyeong Kim

Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of…

Software Engineering · Computer Science 2025-06-23 Kyla H. Levin , Nicolas van Kempen , Emery D. Berger , Stephen N. Freund

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods.…

Computation and Language · Computer Science 2026-05-28 Nora Graichen , Iria de-Dios-Flores , Gemma Boleda

Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and…

Computation and Language · Computer Science 2024-09-24 Zhibo Zhang , Wuxia Bai , Yuxi Li , Mark Huasong Meng , Kailong Wang , Ling Shi , Li Li , Jun Wang , Haoyu Wang