English
Related papers

Related papers: Tool Calling is Linearly Readable and Steerable in…

200 papers

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

Standard LLM benchmarks evaluate the assistant turn: the model generates a response to an input, a verifier scores correctness, and the analysis ends. This paradigm leaves unmeasured whether the LLM encodes any awareness of what follows the…

Artificial Intelligence · Computer Science 2026-04-06 Sarath Shekkizhar , Romain Cosentino , Adam Earle

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

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Computation and Language · Computer Science 2024-10-04 Constanza Fierro , Jiaang Li , Anders Søgaard

Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative…

Computation and Language · Computer Science 2026-05-18 Vinayshekhar Bannihatti Kumar , Disha Makhija , Manoj Ghuhan Arivazhagan , Rashmi Gangadharaiah

Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Chenyu Wang , Weixin Luo , Sixun Dong , Xiaohua Xuan , Zhengxin Li , Lin Ma , Shenghua Gao

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, even when arriving at a correct final answer, their rationales are often logically unsound or inconsistent. This is a major issue when…

Artificial Intelligence · Computer Science 2023-11-09 Gabriel Poesia , Kanishk Gandhi , Eric Zelikman , Noah D. Goodman

Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality. In the current practice of fine-tuning large language models…

Computation and Language · Computer Science 2024-10-07 Dawei Zhu , Pinzhen Chen , Miaoran Zhang , Barry Haddow , Xiaoyu Shen , Dietrich Klakow

Large language models (LLMs) have exhibited the ability to effectively utilize external tools to address user queries. However, their performance may be limited in complex, multi-turn interactions involving users and multiple tools. To…

Computation and Language · Computer Science 2025-03-12 Fan Yin , Zifeng Wang , I-Hung Hsu , Jun Yan , Ke Jiang , Yanfei Chen , Jindong Gu , Long T. Le , Kai-Wei Chang , Chen-Yu Lee , Hamid Palangi , Tomas Pfister

We study planning site formation in language models -- where internal representations of structurally-constrained future tokens form during the forward pass, and whether they causally drive generation. Using rhyming-couplet completion as a…

Machine Learning · Computer Science 2026-05-11 Nicole Ma , Nick Rui

AI developers often apply safety alignment procedures to prevent the misuse of their AI systems. For example, before Meta released Llama 2-Chat - a collection of instruction fine-tuned large language models - they invested heavily in safety…

Machine Learning · Computer Science 2024-05-24 Simon Lermen , Charlie Rogers-Smith , Jeffrey Ladish

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing…

Artificial Intelligence · Computer Science 2025-08-18 Yanming Liu , Xinyue Peng , Jiannan Cao , Yuwei Zhang , Xuhong Zhang , Sheng Cheng , Xun Wang , Jianwei Yin , Tianyu Du

Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, and multi-step reasoning. Current tool-using agents usually expose the executed tool…

Computation and Language · Computer Science 2026-05-12 Bihui Yu , Caijun Jia , Jing Chi , Xiaohan Liu , Yining Wang , He Bai , Yuchen Liu , Jingxuan Wei , Junnan Zhu

Reliable evaluation is essential in machine learning research, yet methodological flaws-particularly data leakage-continue to undermine the validity of reported results. In this work, we investigate whether large language models (LLMs) can…

Computation and Language · Computer Science 2026-04-17 Domonkos Varga

Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters,…

Computation and Language · Computer Science 2026-02-20 Magnus Boman

Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets…

Machine Learning · Computer Science 2024-11-22 Josh Gardner , Juan C. Perdomo , Ludwig Schmidt

Tool-augmented reasoning has emerged as a promising direction for enhancing the reasoning capabilities of multimodal large language models (MLLMs). However, existing studies mainly focus on enabling models to perform tool invocation, while…

Computation and Language · Computer Science 2026-05-20 Qinghe Ma , Zhen Zhao , Yiming Wu , Jian Zhang , Lei Bai , Yinghuan Shi

Large language models (LLMs) are increasingly being adapted to achieve task-specificity for deployment in real-world decision systems. Several previous works have investigated the bias transfer hypothesis (BTH) by studying the effect of the…

Computation and Language · Computer Science 2024-12-05 Natalie Mackraz , Nivedha Sivakumar , Samira Khorshidi , Krishna Patel , Barry-John Theobald , Luca Zappella , Nicholas Apostoloff

Tool learning aims to enhance and expand large language models' (LLMs) capabilities with external tools, which has gained significant attention recently. Current methods have shown that LLMs can effectively handle a certain amount of tools…

Computation and Language · Computer Science 2024-10-01 Qiancheng Xu , Yongqi Li , Heming Xia , Wenjie Li
‹ Prev 1 4 5 6 7 8 10 Next ›