Latest Articles for Language Models

Artificial Intelligence Assessing Planning Skills of OpenAI's o1 Models

A look at how o1 models plan actions and their performance across various tasks.

Kevin Wang, Junbo Li, Neel P. Bhatt

2025-06-03T16:14:06+00:00 ― 7 min read

Computation and Language Analyzing Word Embeddings through Independent Component Analysis

A look into how word embeddings are analyzed using independent component analysis.

Momose Oyama, Hiroaki Yamagiwa, Hidetoshi Shimodaira

2025-06-03T15:58:18+00:00 ― 5 min read

Computation and Language Evaluating Medical Arguments from AI Models

A new method for assessing AI-generated medical explanations using Proxy Tasks.

Iker De la Iglesia, Iakes Goenaga, Johanna Ramirez-Romero

2025-06-03T08:04:18+00:00 ― 5 min read

Computation and Language The Confusion of Large Language Models

Exploring how smaller models struggle with inaccuracies from larger counterparts.

Phil Wee, Riyadh Baghdadi

2025-06-02T09:25:30+00:00 ― 6 min read

Computation and Language LLM-Ref: A New Tool for Research Writing

LLM-Ref aids researchers in crafting clearer, well-structured papers effortlessly.

Kazi Ahmed Asif Fuad, Lizhong Chen

2025-06-02T07:42:48+00:00 ― 6 min read

Computation and Language Can AI Hold a Real Conversation?

Exploring how well AI understands human communication.

Mingyue Jian, Siddharth Narayanaswamy

2025-06-01T01:57:24+00:00 ― 6 min read

Machine Learning Aligning Language Models with Human Preferences

Research shows new methods to better align LLMs with human feedback.

Zichen Liu, Changyu Chen, Chao Du

2025-06-01T00:38:24+00:00 ― 6 min read

Computation and Language Are Machines Creative Storytellers?

A study compares human and AI creativity in storytelling.

Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas

2025-05-31T13:42:42+00:00 ― 6 min read

Software Engineering The Evolving Role of Prompt Engineering with Advanced Models

Assessing prompt engineering's relevance with new reasoning models.

Guoqing Wang, Zeyu Sun, Zhihao Gong

2025-05-31T08:07:48+00:00 ― 7 min read

Databases In-Context Databases: A New Approach

A look at in-context databases and their potential with language models.

Yu Pan, Hongfeng Yu, Tianjiao Zhao

2025-05-31T01:10:12+00:00 ― 5 min read

Computation and Language Multilingual Models in Bilingual Education

Assessing the role of multilingual models in supporting bilingual students.

Anand Syamkumar, Nora Tseng, Kaycie Barron

2025-05-29T18:17:06+00:00 ― 6 min read

Cryptography and Security Challenges in Watermarking AI-Generated Text

Examining vulnerabilities in watermarking methods against paraphrasing attacks.

Saksham Rastogi, Danish Pruthi

2025-05-28T23:21:45+00:00 ― 7 min read

Computation and Language Evaluating Language Models Through Proverbs

Assessing language models' understanding of proverbs in low-resource languages.

Israel Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay

2025-05-28T16:11:06+00:00 ― 5 min read

Computation and Language Bias in Travel Stories and Recommendations

Investigating how wealth influences language models in travel narratives.

Kirti Bhagat, Kinshuk Vasisht, Danish Pruthi

2025-05-26T00:40:30+00:00 ― 7 min read

Computation and Language Improving Language Models with Scar Technology

Scar enhances language models by reducing toxic language in text generation.

Ruben Härle, Felix Friedrich, Manuel Brack

2025-05-25T19:01:12+00:00 ― 5 min read

Computation and Language Using Child Speech to Train Language Models

Research shows variation in speech improves language model training.

Akari Haga, Akiyo Fukatsu, Miyu Oba

2025-05-23T12:25:39+00:00 ― 5 min read

Computation and Language How Prompt Formatting Shapes AI Responses

Explore the impact of question styles on AI model performance.

Jia He, Mukund Rungta, David Koleczek

2025-05-22T18:48:36+00:00 ― 5 min read

Computation and Language Improving Guardrails for Language Models

A new method to develop guardrails for large language models without real-world data.

Gabriel Chua, Shing Yee Chan, Shaun Khoo

2025-05-18T21:42:40+00:00 ― 6 min read

Cryptography and Security Improving Security in Code Generation Models

A new method enhances the safety of code generated by language models.

Xiangzhe Xu, Zian Su, Jinyao Guo

2025-05-18T18:45:20+00:00 ― 5 min read

Software Engineering Evaluating LLMs with SpecTool: A New Approach

SpecTool brings clarity to LLM errors in using tools.

Shirley Kokane, Ming Zhu, Tulika Awalgaonkar

2025-05-16T16:30:40+00:00 ― 4 min read

Computation and Language Risks of Prompt Injection in Language Models

A study reveals how prompt injection can compromise language models.

Jiashuo Liang, Guancheng Li, Yang Yu

2025-05-11T23:21:20+00:00 ― 10 min read

Artificial Intelligence Can LLMs Judge Creativity Fairly?

This study examines how well LLMs assess creativity in the Alternative Uses Test.

Abdullah Al Rabeyah, Fabrício Góes, Marco Volpe

2025-05-11T10:16:00+00:00 ― 5 min read

Machine Learning Balancing Efficiency and Privacy in Language Models

PEFT methods enhance language models while safeguarding private data.

Olivia Ma, Jonathan Passerat-Palmbach, Dmitrii Usynin

2025-05-10T06:49:20+00:00 ― 7 min read

Computation and Language Evaluating Language Models: Shortcuts and Reasoning

A study on how well language models connect facts without shortcuts.

Sohee Yang, Nora Kassner, Elena Gribovskaya

2025-05-09T02:06:40+00:00 ― 7 min read

Computation and Language Improving AI Responses with Self-Critiques

A new method for language models to enhance their responses through self-generated critiques.

Yue Yu, Zhengxing Chen, Aston Zhang

2025-05-09T01:41:20+00:00 ― 6 min read

Machine Learning The Impact of Low-Bit Quantization on Language Models

How low-bit quantization affects large language models during training.

Xu Ouyang, Tao Ge, Thomas Hartvigsen

2025-05-07T00:42:40+00:00 ― 6 min read

Computation and Language Simplifying News Classification with Teacher-Student Models

A new method automates news classification, saving time and resources for organizations.

Taja Kuzman, Nikola Ljubešić

2025-04-30T20:05:20+00:00 ― 4 min read

Computation and Language Assessing Language Models in Spatial Reasoning Tasks

Evaluating if language models can understand spatial relationships effectively.

Anthony G Cohn, Robert E Blackwell

2025-04-30T18:49:20+00:00 ― 6 min read

Machine Learning Enhancing Large Language Models for Better Performance

Discover how to improve large language models in handling symmetric tasks.

Mohsen Dehghankar, Abolfazl Asudeh

2025-04-29T21:42:40+00:00 ― 7 min read

Computation and Language Benchmarking Data Generation in AI Models

Evaluating language models' abilities in synthetic data creation using AgoraBench.

Seungone Kim, Juyoung Suk, Xiang Yue

2025-04-17T19:33:09+00:00 ― 5 min read

Machine Learning The Learning Curve of Language Models

How language models improve their understanding of grammar and sentence structures.

Tian Qin, Naomi Saphra, David Alvarez-Melis

2025-04-12T21:35:06+00:00 ― 8 min read

Computation and Language Transformers and Uncertainty in AI: A Deep Dive

Exploring how transformers can express uncertainty to improve AI reliability.

Greyson Brothers, Willa Mannering, Amber Tien

2025-04-04T19:22:48+00:00 ― 6 min read

Computation and Language The Rosetta Paradox in AI: Breaking Down the Mystery

Large language models excel in some areas but struggle with general tasks.

Basab Jha, Ujjwal Puri

2025-04-01T04:42:36+00:00 ― 7 min read

Machine Learning The Rise of Activation Sparsity in AI Models

Discover how activation sparsity boosts AI efficiency and speed.

Vui Seng Chua, Yujie Pan, Nilesh Jain

2025-03-31T19:04:48+00:00 ― 5 min read

Machine Learning How Language Models Shift: A Deep Dive into BKT Transitions

Explore the connections between language models and physical phenomena in an engaging way.

Yuma Toji, Jun Takahashi, Vwani Roychowdhury

2025-03-31T09:43:04+00:00 ― 9 min read

Computation and Language Unlocking Multi-Step Reasoning in AI

Researchers are improving AI's ability to tackle complex questions with AutoReason.

Arda Sevinc, Abdurrahman Gumus

2025-03-30T16:35:51+00:00 ― 5 min read

Computation and Language Addressing Bias in Filipino Language Models

Researchers tackle biases in language models for Filipino, enhancing cultural relevance.

Lance Calvin Lim Gamboa, Mark Lee

2025-03-24T01:42:09+00:00 ― 5 min read

Computation and Language Evaluating Multilingual Language Models: The English Dilemma

This article examines the complex role of English in multilingual evaluations.

Wessel Poelman, Miryam de Lhoneux

2025-03-20T09:25:39+00:00 ― 7 min read

Machine Learning Sloth: A New Way to Predict AI Performance

Learn how Sloth is changing predictions for language model performance.

Felipe Maia Polo, Seamus Somerstep, Leshem Choshen

2025-03-13T19:32:51+00:00 ― 6 min read

Machine Learning Revolutionizing Language Models with BatchTopK Sparse Autoencoders

BatchTopK sparse autoencoders improve language processing through smart data selection.

Bart Bussmann, Patrick Leask, Neel Nanda

2025-03-13T09:22:29+00:00 ― 5 min read