English
Related papers

Related papers: Systematic Outliers in Large Language Models

200 papers

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These…

Machine Learning · Computer Science 2024-11-08 Tianyu Guo , Druv Pai , Yu Bai , Jiantao Jiao , Michael I. Jordan , Song Mei

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

Computation and Language · Computer Science 2025-03-05 Xinru Lin , Luyang Li

Large Language Models (LLMs) have been found to struggle with systematic reasoning. Even on tasks where they appear to perform well, their performance often depends on shortcuts, rather than on genuine reasoning abilities, leading them to…

Artificial Intelligence · Computer Science 2025-06-03 Irtaza Khalid , Amir Masoud Nourollah , Steven Schockaert

Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathematical computations. However, even for the simplest…

Computation and Language · Computer Science 2024-09-04 Wei Zhang , Chaoqun Wan , Yonggang Zhang , Yiu-ming Cheung , Xinmei Tian , Xu Shen , Jieping Ye

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

Computation and Language · Computer Science 2026-04-13 Hadas Orgad , Boyi Wei , Kaden Zheng , Martin Wattenberg , Peter Henderson , Seraphina Goldfarb-Tarrant , Yonatan Belinkov

Building a theoretical understanding of the capabilities of large language models (LLMs) is vital for our ability to predict and explain the behavior of these systems. Here, we investigate the structure of LLM capabilities by extracting…

Computation and Language · Computer Science 2023-06-21 Ryan Burnell , Han Hao , Andrew R. A. Conway , Jose Hernandez Orallo

Structured output from large language models (LLMs) has enhanced efficiency in processing generated information and is increasingly adopted in industrial applications. Prior studies have investigated the impact of structured output on LLMs'…

Computation and Language · Computer Science 2025-12-22 Han Yuan , Yue Zhao , Li Zhang , Wuqiong Luo , Zheng Ma

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

Machine Learning · Computer Science 2024-04-10 Georgy Tyukin

This paper examines how outliers, often dismissed as noise in topic modeling, can act as weak signals of emerging topics in dynamic news corpora. Using vector embeddings from state-of-the-art language models and a cumulative clustering…

Computation and Language · Computer Science 2025-09-29 Evangelia Zve , Benjamin Icard , Alice Breton , Lila Sainero , Gauvain Bourgne , Jean-Gabriel Ganascia

The rapid advancements in Large Language Models (LLMs) have revolutionized various natural language processing tasks. However, the substantial size of LLMs presents significant challenges in training or fine-tuning. While…

Machine Learning · Computer Science 2025-06-10 Pengxiang Li , Lu Yin , Xiaowei Gao , Shiwei Liu

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in…

Post-training quantization~(PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations. We observe that these outliers are concentrated in specific channels and are…

Computation and Language · Computer Science 2023-10-24 Xiuying Wei , Yunchen Zhang , Yuhang Li , Xiangguo Zhang , Ruihao Gong , Jinyang Guo , Xianglong Liu

The aim of the paper is to show that the presence of one possible type of outliers is not connected to that of heavy tails of the distribution. In contrary, typical situation for outliers appearance is the case of compact supported…

Statistics Theory · Mathematics 2018-07-25 Lev B. Klebanov , Irina Volchenkova

An outlier is an observation or a data point that is far from rest of the data points in a given dataset or we can be said that an outlier is away from the center of mass of observations. Presence of outliers can skew statistical measures…

Machine Learning · Computer Science 2021-06-17 Amulya Agarwal , Nitin Gupta

In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified as the degree of out-of-distribution (OOD) shift. We reveal a consistent and…

Computation and Language · Computer Science 2026-03-20 Mingyu Jin , Yutong Yin , Jingcheng Niu , Qingcheng Zeng , Wujiang Xu , Mengnan Du , Wei Cheng , Zhaoran Wang , Tianlong Chen , Dimitris N. Metaxas

Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…

Computation and Language · Computer Science 2025-12-05 Eshed Gal , Moshe Eliasof , Javier Turek , Uri Ascher , Eran Treister , Eldad Haber

This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations. Although metaphor processing has gained significant…

Computation and Language · Computer Science 2025-07-22 Elisa Sanchez-Bayona , Rodrigo Agerri