LLM Fine-Tuning

LLM: Large Language Model

LLM fine-tuning studies how additional training can adapt a pretrained model to new tasks, specialized knowledge, languages, or desired behaviors. Common approaches include supervised fine-tuning on curated or synthetic examples, preference optimization and reinforcement learning, and parameter-efficient methods such as LoRA and QLoRA that update only a small part of the model. Researchers also develop data-selection methods and selective layer or neuron updates to reduce training cost, and evaluate results on settings such as reasoning, code generation, multilingual tasks, and domain-specific question answering. A central challenge is gaining reliable task performance without losing general abilities or safety; results depend on the data, model, and evaluation, and retrieval can sometimes be a better alternative for adding knowledge.

Latest papers

758 papers76 papers in the last four weeks, up 15% on the four weeks before. 0.4% of all new papers.

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
Domain-Adapted Small Language Models for Reliable Clinical Triage
Apr 29, 2026Manar Aljohani, Brandon Ho, Kenneth McKinley +2Clinical Triage LLM Fine-Tuning
Department of Computer Science, Virginia Tech, Blacksburg, VA, US · Children’s National Hospital, Washington DC, USA
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Apr 29, 2026Jinho Choo, JunSeung Lee, Jimyeong Kim +3Multilingual Language Models RL for Language Models
Samsung SDS
SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning
Apr 29, 2026Yimeng Shan, Zhaorui Zhang, Sheng Di +3Communication-Efficient Distributed Training LLM Fine-Tuning
Hong Kong Polytechnic University Hong Kong · Argonne National Labratory USA · University of California, Merced USA +1
Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning
Apr 29, 2026Weihang Li, Jianchun Liu, Hongli XuMixture-of-Experts Pruning LLM Fine-Tuning
School of Computer Science and Technology, University of Science and Technology of China, China · Suzhou Institute for Advanced Research, University of Science and Technology of China, China
EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
Apr 28, 2026Ting-Wei Li, Sirui Chen, Jiaru Zou +4LLM Fine-Tuning Synthetic Data Generation
University of Illinois Urbana-Champaign
G-Loss: Graph-Guided Fine-Tuning of Language Models
Apr 28, 2026Aditya Sharma, Vinti Agarwal, Rajesh KumarLLM Fine-Tuning Text Classification
BITS Pilani, India · Bucknell University, USA
Benchmarking PyCaret AutoML Against IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian IKN Twitter Data
Apr 28, 2026Mutia Alfi Mayzaroh, Dwi Fitria Ningsih, Nindi Destriani +1Social Media Analysis LLM Fine-Tuning
Institut Teknologi Sumatera Lampung Selatan, Indonesia
LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model
Apr 28, 2026Youngjoon Jang, Chanhee Park, Hyeonseok Moon +5Legal NLP LLM Fine-Tuning
Department of Computer Science and Engineering, Korea University · KT (Korea Telecom)
BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
Apr 28, 2026Arnon Mazza, Elad LeviLLM Guardrails LLM Fine-Tuning
Plurai Inc.
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
Apr 28, 2026Ling Shi, Xinwei Wu, Xiaohu Zhao +7LLM Fine-Tuning Data Selection for Language Model Fine-Tuning
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · Alibaba Group, China
Contextual Linear Activation Steering of Language Models
Apr 27, 2026Brandon Hsu, Daniel Beaglehole, Adityanarayanan Radhakrishnan +1Language Model Steering LLM Fine-Tuning
UC San Diego · MIT · Broad Institute of MIT and Harvard
Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study
Apr 27, 2026Sivajeet Chand, Kevin Nguyen, Peter Kuntz +1LLM Fine-Tuning Code Generation
Technical University of Munich · Munich, Germany · BMW Group
A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
Apr 27, 2026Zihan Liu, Yizhen Wang, Rui Wang +2Privacy-Preserving Language Models LLM Fine-Tuning
Zhejiang University, Ningbo, China
Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale
Apr 26, 2026Avi-ad Avraam BuskilaRetrieval-Augmented Generation Healthcare
Department of Information Science and Applied Artificial Intelligence, Bar-Ilan University, Ramat-Gan, Israel
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
Apr 26, 2026Shuaizhi Cheng, Xiang Shi, Zhiwei Zhang +1Knowledge Conflicts in Language Models LLM Fine-Tuning
Harbin Institute of Technology · KigLand Machine Learning Lab · Imperial College London
Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer
Apr 26, 2026Ahmed Haj Ahmed, Ruochen Zhang, Alvin GrissomMultilingual Language Model Evaluation LLM Fine-Tuning
Haverford College · Brown University
$\mathcal{S}^2$ IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
Apr 25, 2026Bingfeng Chen, Chenjie Qiu, Yifeng Xie +3LLM Fine-Tuning Aspect-Based Sentiment Analysis
School of Computer Science, Guangdong University of Technology · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Peng Cheng Laboratory +1
Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective
Apr 25, 2026Bishwamittra Ghosh, Soumi Das, Till Speicher +5LLM Evaluation LLM Fine-Tuning
Max Planck Institute for Software Systems, Germany · Boston University, USA
DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
Apr 24, 2026Youze Zheng, Jianyou Wang, Yuhan Chen +8LLM Fine-Tuning Counterfactual Reasoning in Language Models
Laboratory for Emerging Intelligence, University of California, San Diego · University of Chicago · Elsevier +1
Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge
Apr 24, 2026Mengyu Wang, Xiaoying Zhi, Zhiyi Li +4Document Understanding LLM Fine-Tuning
1The University of Edinburgh · 2JPMorgan Chase & Co.
mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
Apr 23, 2026Adam Skurla, Dominik Macko, Jakub SimkoAI-Generated Text Detection LLM Fine-Tuning
Faculty of Information Technology, Brno University of Technology, Brno, Czechia · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia
CARE: Counselor-Aligned Response Engine for Online Mental-Health Support
Apr 23, 2026Hagai Astrin, Ayal Swaid, Avi Segal +1Mental Health Counseling Emotional Support Conversation
Ben-Gurion University · School of Informatics, University of Edinburgh Edinburgh, UK
Align Generative Artificial Intelligence with Human Preferences: A Novel Large Language Model Fine-Tuning Method for Online Review Management
Apr 23, 2026Yanan Wang, Yong GeLLM Hallucination Mitigation LLM Fine-Tuning
Department of Information Systems and Operations Management, The University of Texas at Arlington · Department of Management Information Systems, University of Arizona
AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models
Apr 22, 2026Tadesse Destaw Belay, Shahriar Kabir Nahin, Israel Abebe Azime +6Multilingual Language Models Intelligent Tutoring Systems
Instituto Politécnico Nacional, Mexico · University of South Florida, FL, USA · Saarland University, Germany +2
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
Apr 22, 2026Noah FlynnMultilingual Language Models Continual Learning for LLMs
UC Berkeley
Compatibility-Aware Dynamic Fine-Tuning for Large Language Models
Apr 22, 2026Yucheng Zhou, Junwei Sheng, Qianning Wang +1Supervised Fine-Tuning Fine-Tuning
SKL-IOTSC, CIS, University of Macau · Auckland University of Technology
IRIS: Interpolative Rényi Iterative Self-play for Large Language Model Fine-Tuning
Apr 22, 2026Wenjie Liao, Like Wu, Liangjie Zhao +2Fine-Tuning LLM Fine-Tuning
Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan · Institute of Computing Technology, University of the Chinese Academy of Sciences
RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
Apr 21, 2026Yusuf Çelebi, Yağız Asker, Özay Ezerceli +4LLM Fine-Tuning Low-Rank Adaptation
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
Apr 21, 2026Tao Fan, Guoqiang Ma, Yuanfeng Song +3Privacy-Preserving Language Models LLM Fine-Tuning
Hong Kong University of Science and Technology, Hong Kong, China · WeBank Co., Ltd, Shenzhen, China · Hong Kong Polytechnic University, Hong Kong, China

Apr 29, 2026J/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.