English
Related papers

Related papers: Incompressible Knowledge Probes: Estimating Black-…

200 papers

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Artificial Intelligence · Computer Science 2025-11-21 Parshin Shojaee , Iman Mirzadeh , Keivan Alizadeh , Maxwell Horton , Samy Bengio , Mehrdad Farajtabar

Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted to integrate external knowledge into PLMs. However, despite…

Computation and Language · Computer Science 2023-10-12 Yunzhi Yao , Peng Wang , Shengyu Mao , Chuanqi Tan , Fei Huang , Huajun Chen , Ningyu Zhang

Evaluating knowledge systems (LLMs, RAG, knowledge graphs, etc) faces fundamental challenges: static benchmarks are vulnerable to contamination, LLM-based judges exhibit systematic biases, and ground truth extraction requires expensive…

Computation and Language · Computer Science 2026-01-16 JV Roig

Lossy compressors are increasingly adopted in scientific research, tackling volumes of data from experiments or parallel numerical simulations and facilitating data storage and movement. In contrast with the notion of entropy in lossless…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-16 Robert Underwood , Julie Bessac , David Krasowska , Jon C. Calhoun , Sheng Di , Franck Cappello

Zero-knowledge proofs (ZKPs) are increasingly deployed in domains such as privacy-preserving authentication, verifiable computation, and secure finance. However, authoring ZK programs remains challenging: unlike conventional software…

Software Engineering · Computer Science 2026-02-03 Zhantong Xue , Pingchuan Ma , Zhaoyu Wang , Yuguang Zhou , Xiaoqin Zhang , Shuai Wang , Juergen Rahmel

Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative…

Computation and Language · Computer Science 2020-11-24 Xiaozhi Wang , Tianyu Gao , Zhaocheng Zhu , Zhengyan Zhang , Zhiyuan Liu , Juanzi Li , Jian Tang

Deep neural networks have become foundational to advancements in multiple domains, including recommendation systems, natural language processing, and so on. Despite their successes, these models often contain incompatible parameters that…

Machine Learning · Computer Science 2025-03-04 Zheqi Lv , Keming Ye , Zishu Wei , Qi Tian , Shengyu Zhang , Wenqiao Zhang , Wenjie Wang , Kun Kuang , Tat-Seng Chua , Fei Wu

Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by…

Computation and Language · Computer Science 2022-10-18 Jianing Wang , Wenkang Huang , Qiuhui Shi , Hongbin Wang , Minghui Qiu , Xiang Li , Ming Gao

Compression methods, including quantization, distillation, and pruning, improve the computational efficiency of large reasoning models (LRMs). However, existing studies either fail to sufficiently compare all three compression methods on…

Machine Learning · Computer Science 2026-03-03 Nan Zhang , Eugene Kwek , Yusen Zhang , Ngoc-Hieu Nguyen , Prasenjit Mitra , Rui Zhang

While question-answering~(QA) benchmark performance is an automatic and scalable method to compare LLMs, it is an indirect method of evaluating their underlying problem-solving capabilities. Therefore, we propose a holistic and…

Computation and Language · Computer Science 2025-08-01 Yunxiang Yan , Tomohiro Sawada , Kartik Goyal

Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge. However, it remains unclear how well LLMs are able to perceive their factual knowledge boundaries, particularly under…

Computation and Language · Computer Science 2024-11-20 Ruiyang Ren , Yuhao Wang , Yingqi Qu , Wayne Xin Zhao , Jing Liu , Hao Tian , Hua Wu , Ji-Rong Wen , Haifeng Wang

Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often…

Databases · Computer Science 2020-03-27 Shrestha Ghosh , Simon Razniewski , Gerhard Weikum

We present a longitudinal study which evaluates the reasoning capability of frontier Large Language Models over an eighteen month period. We measured the accuracy of three leading models from December 2023, September 2024 and June 2025 on…

Artificial Intelligence · Computer Science 2025-09-17 Lachlan McGinness , Peter Baumgartner

Factual knowledge encoded in Pre-trained Language Models (PLMs) enriches their representations and justifies their use as knowledge bases. Previous work has focused on probing PLMs for factual knowledge by measuring how often they can…

Computation and Language · Computer Science 2024-02-05 Paul Youssef , Jörg Schlötterer , Christin Seifert

Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge might be insufficient…

Computation and Language · Computer Science 2023-06-08 Jinheon Baek , Alham Fikri Aji , Amir Saffari

Recent large language models often answer factual questions correctly. But users can't trust any given claim a model makes without fact-checking, because language models can hallucinate convincing nonsense. In this work we use reinforcement…

The standard formalization of preprocessing in parameterized complexity is given by kernelization. In this work, we depart from this paradigm and study a different type of preprocessing for problems without polynomial kernels, still aiming…

Data Structures and Algorithms · Computer Science 2025-12-16 Michał Włodarczyk

We propose and analyze a family of information processing systems, where a finite set of experts or servers are employed to extract information about a stream of incoming jobs. Each job is associated with a hidden label drawn from some…

Probability · Mathematics 2016-05-31 Laurent Massoulie , Kuang Xu

Research on mental state reasoning in language models (LMs) has the potential to inform theories of human social cognition--such as the theory that mental state reasoning emerges in part from language exposure--and our understanding of LMs…

Computation and Language · Computer Science 2026-02-19 Sean Trott , Samuel Taylor , Cameron Jones , James A. Michaelov , Pamela D. Rivière

LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems truly understand mathematical structure as humans do? We investigate this…

Artificial Intelligence · Computer Science 2025-10-21 Haoyu Zhao , Yihan Geng , Shange Tang , Yong Lin , Bohan Lyu , Hongzhou Lin , Chi Jin , Sanjeev Arora