English
Related papers

Related papers: How Context Shapes Truth: Geometric Transformation…

200 papers

Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasized mid-context degradation in question answering, this…

Computation and Language · Computer Science 2026-02-25 Pietro Bernardelle , Stefano Civelli , Kevin Roitero , Gianluca Demartini

Recent work has demonstrated that the latent spaces of large language models (LLMs) contain directions predictive of the truth of sentences. Multiple methods recover such directions and build probes that are described as uncovering a…

Computation and Language · Computer Science 2025-07-14 Stefan F. Schouten , Peter Bloem , Ilia Markov , Piek Vossen

Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesized to facilitate next-token prediction via linear…

Computation and Language · Computer Science 2026-02-02 Eghbal A. Hosseini , Yuxuan Li , Yasaman Bahri , Declan Campbell , Andrew Kyle Lampinen

Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM's internal activations.…

Artificial Intelligence · Computer Science 2024-08-20 Samuel Marks , Max Tegmark

Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly…

Computation and Language · Computer Science 2026-02-10 Dingzirui Wang , Xuanliang Zhang , Keyan Xu , Qingfu Zhu , Wanxiang Che , Yang Deng

One of the most striking features of Large Language Models (LLMs) is their ability to learn in-context. Namely at inference time an LLM is able to learn new patterns without any additional weight update when these patterns are presented in…

Computation and Language · Computer Science 2025-12-24 Benoit Dherin , Michael Munn , Hanna Mazzawi , Michael Wunder , Javier Gonzalvo

Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent hypothesis space over which this inference operates remains unclear. In this work, we…

Computation and Language · Computer Science 2026-05-13 Eric Bigelow , Raphaël Sarfati , Daniel Wurgaft , Owen Lewis , Thomas McGrath , Jack Merullo , Atticus Geiger , Ekdeep Singh Lubana

Large language models (LLMs) have demonstrated remarkable progress in leveraging diverse knowledge sources. This study investigates how nine widely used LLMs allocate knowledge between local context and global parameters when answering…

Computation and Language · Computer Science 2024-11-22 Yufei Tao , Adam Hiatt , Erik Haake , Antonie J. Jetter , Ameeta Agrawal

In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions. The…

Computation and Language · Computer Science 2023-12-22 Xiang Li , Haoran Tang , Siyu Chen , Ziwei Wang , Anurag Maravi , Marcin Abram

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…

Artificial Intelligence · Computer Science 2025-11-11 Hirohane Takagi , Gouki Minegishi , Shota Kizawa , Issey Sukeda , Hitomi Yanaka

Large Language Models (LLMs) have demonstrated impressive generalization capabilities across various tasks, but their claim to practical relevance is still mired by concerns on their reliability. Recent works have proposed examining the…

Machine Learning · Computer Science 2025-07-08 Waiss Azizian , Michael Kirchhof , Eugene Ndiaye , Louis Bethune , Michal Klein , Pierre Ablin , Marco Cuturi

Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture of context-augmented and context-free examples, yet prior…

Computation and Language · Computer Science 2026-01-09 Hyunji Lee , Seunghyun Yoon , Yunjae Won , Hanseok Oh , Geewook Kim , Trung Bui , Franck Dernoncourt , Elias Stengel-Eskin , Mohit Bansal , Minjoon Seo

As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context. This requires LLMs to possess both context-faithfulness and factual…

Computation and Language · Computer Science 2024-10-07 Baolong Bi , Shenghua Liu , Yiwei Wang , Lingrui Mei , Junfeng Fang , Hongcheng Gao , Shiyu Ni , Xueqi Cheng

Large Language Models (LLMs) exhibit strong conversational abilities but often generate falsehoods. Prior work suggests that the truthfulness of simple propositions can be represented as a single linear direction in a model's internal…

Machine Learning · Computer Science 2025-05-29 Stanley Yu , Vaidehi Bulusu , Oscar Yasunaga , Clayton Lau , Cole Blondin , Sean O'Brien , Kevin Zhu , Vasu Sharma

Despite the great success of large language models (LLMs) in various tasks, they suffer from generating hallucinations. We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using…

Computation and Language · Computer Science 2024-01-19 Zhongzhi Chen , Xingwu Sun , Xianfeng Jiao , Fengzong Lian , Zhanhui Kang , Di Wang , Cheng-Zhong Xu

Large language models (LLMs) have been shown to encode truth of statements in their activation space along a linear truth direction. Previous studies have argued that these directions are universal in certain aspects, while more recent work…

Computation and Language · Computer Science 2026-04-07 Angelos Poulis , Mark Crovella , Evimaria Terzi

Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains…

Machine Learning · Computer Science 2026-02-09 Long Zhang , Fangwei Lin

Large language models (LLMs) are increasingly strong contenders in machine translation. In this work, we focus on document-level translation, where some words cannot be translated without context from outside the sentence. Specifically, we…

Computation and Language · Computer Science 2025-02-17 Wafaa Mohammed , Vlad Niculae

Existing explainability methods for Large Language Models (LLMs) typically treat hidden states as static points in activation space, assuming that correct and incorrect inferences can be separated using representations from an individual…

Computation and Language · Computer Science 2026-03-03 Hamed Damirchi , Ignacio Meza De la Jara , Ehsan Abbasnejad , Afshar Shamsi , Zhen Zhang , Javen Shi

Transformer-based large language models (LLMs) typically have a limited context window, resulting in significant performance degradation when processing text beyond the length of the context window. Extensive studies have been proposed to…

Computation and Language · Computer Science 2024-11-19 Zican Dong , Junyi Li , Xin Men , Wayne Xin Zhao , Bingbing Wang , Zhen Tian , Weipeng Chen , Ji-Rong Wen
‹ Prev 1 2 3 10 Next ›