Factual Knowledge in Language Models

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 38% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 117

All topics

MoRFI: Monotonic Sparse Autoencoder Feature Identification
Apr 29, 2026Dimitris Dimakopoulos, Shay B. Cohen, Ioannis KonstasLLM Hallucination Mitigation LLM Interpretability
University of Edinburgh, UK · Heriot-Watt University, UK
Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity
Apr 27, 2026Bojie LiParameter Estimation LLM Evaluation
Pine AI
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Apr 27, 2026Chenkai Pan, Xinglong Xu, Yuhang Xu +6LLM Evaluation Knowledge Augmentation for Language Models
Zhejiang University · University of Chinese Academy of Sciences · Shanghai Artificial Intelligence Laboratory
Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms
Apr 23, 2026Yuto Nishida, Naoki Shikoda, Yosuke Kishinami +4LLM Evaluation Memorization in Language Models
Nara Institute of Science and Technology · Future Corporation
Tracing Relational Knowledge Recall in Large Language Models
Apr 21, 2026Nicholas Popovič, Michael FärberLinear Probing Factual Knowledge in Language Models
TU Dresden & ScaDS.AI Dresden/Leipzig, Germany
Structure Guided Retrieval-Augmented Generation for Factual Queries
Apr 21, 2026Miao Xie, Xiao Zhang, Yi Li +1Graph Retrieval-Augmented Generation Factual Knowledge in Language Models
College of Information and Electrical Engineering, China Agricultural University, China · College of Computing and Data Science, Nanyang Technological University, Singapore · Key Laboratory of Agricultural Informatization Standardization, Ministry of Agriculture and Rural Affairs, China
Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?
Apr 21, 2026Sho Hoshino, Ukyo Honda, Peinan ZhangSelf-Consistency Decoding CoT Reasoning
CyberAgent
KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models
Apr 19, 2026Xiao Zhang, Qianru Meng, Yongjian Chen +2LLM Evaluation Compositional Reasoning
University of Groningen · LIACS, Leiden University
One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them
Apr 18, 2026Ali Holmov, Paul Youssef, Nandi Schoots +1Knowledge Editing Transformer Interpretability
Technical University of Munich · Marburg University · University of Oxford
Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
Apr 18, 2026Jiang Zhou, Xiaohu Zhao, Xinwei Wu +8RL for Language Models Factual Knowledge in Language Models
TJUNLP Lab, Tianjin University, China · Alibaba Group, China
BAGEL: Benchmarking Animal Knowledge Expertise in Language Models
Apr 17, 2026Jiacheng Shen, Masato Hagiwara, Milad Alizadeh +9LLM Evaluation Question Answering
2NYU Center for Data Science; NYU Shanghai · 1Earth Species Project · 3NYU Shanghai Center for Data Science; NYU-ECNU Institute of Mathematical Sciences at NYU Shanghai
CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
Apr 16, 2026Seyun Bae, Seokhan Lee, Eunho YangPrivacy-Preserving Language Models Factual Knowledge in Language Models
1KT Corporation · 2KAIST
World Properties without World Models: Distributional Associations and the Interpretation of Decoding Results from Language Models
Mar 4, 2026Elan BarenholtzLLM World Models Word Embeddings
Department of Psychology & Center for Complex Systems and Brain Sciences Florida Atlantic University
Probing for Knowledge Attribution in Large Language Models
Feb 26, 2026Ivo Brink, Alexander Boer, Dennis UlmerLLM Interpretability Hallucination in Language Models
KPMG NL / University of Amsterdam Amsterdam, The Netherlands · KPMG NL Amsterdam, The Netherlands · University of Amsterdam Amsterdam, The Netherlands
How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing
Feb 25, 2026Javier MarínTransformer Interpretability LLM Interpretability
Groundlens-dev
MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering
Jan 21, 2026Anjishnu Mukherjee, Ziwei Zhu, Antonios AnastasopoulosLanguage Model Pretraining LLM Evaluation
George Mason University
Relational Linearity is a Predictor of Hallucinations
Jan 16, 2026Yuetian Lu, Yihong Liu, Sebastian Gerstner +3LLM Interpretability Hallucination in Language Models
Center for Information and Language Processing (CIS), LMU Munich · Ubiquitous Knowledge Processing Lab (UKP Lab), Technical University of Darmstadt · Munich Center for Machine Learning (MCML)
Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs
Nov 8, 2025Renfei Zhang, Manasa Kaniselvan, Rylan Schaeffer abd Niloofar MireshghallahRL for Language Model Reasoning Factual Knowledge in Language Models
Carnegie Mellon University · MIT · Stanford University
Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
Nov 3, 2025Sekh Mainul Islam, Pepa Atanasova, Isabelle AugensteinDisentangled Representation Learning LLM Grounding
University of Copenhagen
Zoom In Disparities in Healthcare LLM Q&A
Oct 20, 2025Ipek Baris Schlicht, Burcu Sayin, Zhixue Zhao +5Multilingual Language Model Evaluation Knowledge Augmentation for Language Models
Universitat Politècnica de València, Valencia, Spain · University of Trento, Trento, Italy · University of Sheffield, Sheffield, UK +5
What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models
Oct 5, 2025Dustin Wright, Sarah Masud, Jared Moore +5LLM Evaluation Cultural Bias in Language Models
University of Copenhagen · Stanford University · University of Colorado Boulder +1
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Sep 3, 2025Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen +4Language Model Pretraining Knowledge Editing
Tel Aviv University · Mila – Quebec AI Institute & McGill University
GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
Jul 8, 2025Yujia Hu, Tuan-Phong Nguyen, Shrestha Ghosh +2KG Construction LLM Information Extraction
ScaDS.AI Dresden/Leipzig & TU Dresden, Germany · VNU University of Engineering and Technology, Hanoi, Vietnam · University of Tübingen, Germany
Language Specific Knowledge: Do Models Know Better in X than in English?
May 21, 2025Ishika Agarwal, Nimet Beyza Bozdag, Dilek Hakkani-TürMultilingual Language Models Multilingual QA
Department of Computer Science University of Illinois, Urbana-Champaign
Continual Memorization of Factoids in Language Models
Nov 11, 2024Howard Chen, Jiayi Geng, Adithya Bhaskar +2Continual Learning for LLMs Memorization in Language Models
Princeton Language and Intelligence (PLI), Princeton University
All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
Date pendingAdvait Deshmukh, Ashwin Umadi, Dananjay Srinivas +1Language Model Pretraining Long-Tail Learning
University of Colorado Boulder
KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs
Date pendingDonghyeon Ko, Kyubyung Chae, Yeguk Jin +6Multilingual Language Model Evaluation LLM Evaluation
Naver Cloud · Graduate School of Data Science, Seoul National University

Apr 29, 2026, cs.CLJ/K move · Enter open · S save

MoRFI: Monotonic Sparse Autoencoder Feature Identification

Dimitris Dimakopoulos, Shay B. Cohen, Ioannis Konstas

University of Edinburgh, UK · Heriot-Watt University, UK

LLM Hallucination Mitigation LLM Interpretability LLM Fine-Tuning Hallucination in Language Models Sparse Autoencoders LLM Reliability+2

Open paper AskPDF arXiv

Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training often introduce new facts outwith the parametric knowledge, giving rise to hallucinations. While it has been demonstrated that supervised fine-tuning (SFT) on new knowledge may exacerbate the problem, the underlying mechanisms are still poorly understood. We conduct a controlled fine-tuning experiment, focusing on closed-book QA, and find latent directions that causally contribute to hallucinations. Specifically, we fine-tune Llama 3.1 8B, Gemma 2 9B and Mistral 7B v03 on seven distinct single QA datasets, controlling for the percentage of new knowledge and number of training epochs. By measuring performance on the test set, we validate that incrementally introducing new knowledge increases hallucinations, with the effect being more pronounced with prolonged training. We leverage pre-trained sparse autoencoders (SAEs) to analyze residual stream activations across various checkpoints for each model and propose Monotonic Relationship Feature Identification (MoRFI) for capturing causally relevant latents. MoRFI filters SAE features that respond monotonically to controlled fine-tuning data mixtures of a target property. Our findings show that exposure to unknown facts disrupts the model's ability to retrieve stored knowledge along a set of directions in the residual stream. Our pipeline reliably discovers them across distinct models, recovering knowledge through single-latent interventions.

Momentum

Related topics

Latest papers 117