English
Related papers

Related papers: When Self-Reference Fails to Close: Matrix-Level D…

200 papers

We propose Curved Inference - a geometric Interpretability framework that tracks how the residual stream trajectory of a large language model bends in response to shifts in semantic concern. Across 20 matched prompts spanning emotional,…

Computation and Language · Computer Science 2025-07-30 Rob Manson

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Machine Learning · Computer Science 2026-05-20 Zhipeng Zhang

This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements…

Computation and Language · Computer Science 2025-03-13 Sagi Shaier , Mario Sanz-Guerrero , Katharina von der Wense

Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across…

Computation and Language · Computer Science 2026-05-05 Ranit Karmakar , Jayita Chatterjee

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Computation and Language · Computer Science 2025-06-13 Jaechul Roh , Varun Gandhi , Shivani Anilkumar , Arin Garg

Large language models produce rich introspective language when prompted for self-examination, but whether this language reflects internal computation or sophisticated confabulation has remained unclear. We show that self-referential…

Computation and Language · Computer Science 2026-02-19 Zachary Pedram Dadfar

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of…

Machine Learning · Computer Science 2026-05-22 Pavel Golikov , Evgenii Opryshko , Gennady Pekhimenko , Mark C. Jeffrey

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

Computation and Language · Computer Science 2025-05-21 Hongru Wang , Deng Cai , Wanjun Zhong , Shijue Huang , Jeff Z. Pan , Zeming Liu , Kam-Fai Wong

Routing is widely used to scale large language models, from Mixture-of-Experts gating to multi-model/tool selection. A common belief is that routing to a task ``expert'' activates sparser internal computation and thus yields more certain…

Artificial Intelligence · Computer Science 2026-04-01 Dianxing Zhang , Gang Li , Sheng Li

Large language models require consistent behavioral patterns for safe deployment, yet there are indications of large variability that may lead to an instable expression of personality traits in these models. We present PERSIST (PERsonality…

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability…

Artificial Intelligence · Computer Science 2026-04-15 Wenkai Li , Fan Yang , Shaunak A. Mehta , Koichi Onoue

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Computation and Language · Computer Science 2026-04-28 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

We discover that large language models exhibit \emph{spectral phase transitions} in their hidden activation spaces when engaging in reasoning versus factual recall. Through systematic spectral analysis across \textbf{11 models} spanning…

Machine Learning · Computer Science 2026-04-20 Yi Liu

Large language models (LLMs) have achieved strong performance on medical question answering (medical QA), and chain-of-thought (CoT) prompting has further improved results by eliciting explicit intermediate reasoning; meanwhile,…

Computation and Language · Computer Science 2026-04-03 Zaifu Zhan , Mengyuan Cui , Rui Zhang

The versatility of Large Language Models (LLMs) on natural language understanding tasks has made them popular for research in social sciences. To properly understand the properties and innate personas of LLMs, researchers have performed…

Computation and Language · Computer Science 2024-04-03 Bangzhao Shu , Lechen Zhang , Minje Choi , Lavinia Dunagan , Lajanugen Logeswaran , Moontae Lee , Dallas Card , David Jurgens

Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries…

Cryptography and Security · Computer Science 2026-04-14 Honghao Liu , Chengjin Xu , Xuhui Jiang , Cehao Yang , Shengming Yin , Zhengwu Ma , Lionel Ni , Jian Guo

Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-box methods compress high-dimensional…

Artificial Intelligence · Computer Science 2026-04-14 Nicolas Martorell , Bruno Bianchi

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Artificial Intelligence · Computer Science 2025-04-02 Yu Cui , Bryan Hooi , Yujun Cai , Yiwei Wang

This paper investigates how prompt engineering techniques impact both accuracy and confidence elicitation in Large Language Models (LLMs) applied to medical contexts. Using a stratified dataset of Persian board exam questions across…

Computers and Society · Computer Science 2025-06-03 Nariman Naderi , Zahra Atf , Peter R Lewis , Aref Mahjoub far , Seyed Amir Ahmad Safavi-Naini , Ali Soroush
‹ Prev 1 2 3 10 Next ›