NeuroGenesysThe research we build on.
1,514 papers by other researchers that our work cites, from continual learning and verification to language models, agents and hardware. Each entry links to the paper on arXiv and to where we use it. 301 are cited on published pages of this site; the rest in the research notes behind our studies. Our own papers are in the archive.
- 2024-10arXiv 2410.03122RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning
Zihao Zhao, Yuchen Yang, Yijiang Li et al. · Language models & NLP
The ripple effect poses a significant challenge in knowledge editing for large language models. Namely, when a single fact is edited, the model struggles to accurately update the related facts in a sequence, which is evaluated by multi-hop questions linked to a chain of related facts.
- 2024-10arXiv 2410.02330Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
Tianxiang Chen, Zhentao Tan, Tao Gong et al. · Language models & NLP
As a manner to augment pre-trained large language models (LLM), knowledge injection is critical to develop vertical domain large models and has been widely studied.
- 2024-09arXiv 2409.18025An Adversarial Perspective on Machine Unlearning for AI Safety
Jakub Łucki, Boyi Wei, Yangsibo Huang et al. · Machine learning
Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to adversaries.
- 2024-08arXiv 2408.13656Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Yifei He, Yuzheng Hu, Yong Lin et al. · Machine learning
Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each.
- 2024-06arXiv 2406.16797Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Ashwinee Panda, Berivan Isik, Xiangyu Qi et al. · Language models & NLP
Existing methods for adapting large language models (LLMs) to new tasks are not suited to multi-task adaptation because they modify all the model weights -- causing destructive interference between tasks.
- 2024-06arXiv 2406.13356Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu et al. · Machine learning
Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of .
- 2024-06arXiv 2406.04496Time Sensitive Knowledge Editing through Efficient Finetuning
Xiou Ge, Ali Mousavi, Edouard Grave et al. · Language models & NLP
Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is complete.
- 2024-05arXiv 2405.14117Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
Yuheng Chen, Pengfei Cao, Yubo Chen et al. · Language models & NLP
Large language models (LLMs) store extensive factual knowledge, but the mechanisms behind how they store and express this knowledge remain unclear. The Knowledge Neuron (KN) thesis is a prominent theory for explaining these mechanisms.
- 2024-04arXiv 2404.18466HFT: Half Fine-Tuning for Large Language Models
Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang et al. · Language models & NLP
Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences.
- 2024-03arXiv 2403.08994Ethos: Rectifying Language Models in Orthogonal Parameter Space
Lei Gao, Yue Niu, Tingting Tang et al. · Language models & NLP
Language models (LMs) have greatly propelled the research on natural language processing. However, LMs also raise concerns regarding the generation of biased or toxic content and the potential disclosure of private information from the training dataset.
- 2024-03arXiv 2403.00745AtP*: An efficient and scalable method for localizing LLM behaviour to components
János Kramár, Tom Lieberum, Rohin Shah et al. · Machine learning
Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling linearly in the number of model components, which can be prohibitively expensive for SoTA Large Language Models (LLMs).
- 2024-02arXiv 2402.11746Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
Rishabh Bhardwaj, Do Duc Anh, Soujanya Poria · Language models & NLP
Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment.
- 2024-02arXiv 2402.12048Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
Didi Zhu, Zhongyi Sun, Zexi Li et al. · Language models & NLP
Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a significant performance drop on the original tasks.
- 2024-02arXiv 2402.10058Towards Safer Large Language Models through Machine Unlearning
Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan et al. · Language models & NLP
The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability.
- 2023-12arXiv 2312.06795Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
MohammadReza Davari, Eugene Belilovsky · Machine learning
The rapid development of AI systems has been greatly influenced by the emergence of foundation models.
- 2023-12arXiv 2312.05497History Matters: Temporal Knowledge Editing in Large Language Model
Xunjian Yin, Jin Jiang, Liming Yang et al. · Language models & NLP
The imperative task of revising or updating the knowledge stored within large language models arises from two distinct sources: intrinsic errors inherent in the model which should be corrected and outdated knowledge due to external shifts in the real world which should be updated.
- 2023-11arXiv 2311.08011Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models
Shiwen Ni, Dingwei Chen, Chengming Li et al. · Language models & NLP
Recent advancements in Large Language Models (LLMs) have showcased their remarkable capabilities in text understanding and generation. However, even stronger LLMs are susceptible to acquiring erroneous or obsolete information from the training corpus.
- 2023-11arXiv 2311.03099Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Le Yu, Bowen Yu, Haiyang Yu et al. · Language models & NLP
In this paper, we unveil that Language Models (LMs) can acquire new capabilities by assimilating parameters from homologous models without retraining or GPUs.
- 2023-06arXiv 2306.01708TIES-Merging: Resolving Interference When Merging Models
Prateek Yadav, Derek Tam, Leshem Choshen et al. · Machine learning
, further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency.
Cited inStudy: Decision signatures for conflict detectionStudy: Fortifying knowledge in continual learningStudy: Generational competitive continual learningStudy: Hierarchical and T shaped MoEStudy: LLMs modifying open model weightsStudy: Merging and splitting MoE expertsStudy: Weight editing to prevent forgetting - 2023-05arXiv 2305.14795MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning et al. · Language models & NLP
The information stored in large language models (LLMs) falls out of date quickly, and retraining from scratch is often not an option. This has recently given rise to a range of techniques for injecting new facts through updating model weights.
Cited inTrust the premises, not the confidence: which belief to drop when an LLM contradicts itself, and why the solver is not the bottleneckStudy: Consequence consistent updatesStudy: Continual learning order and companion dataStudy: Graded succession by earned authorityStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesisStudy: Weight editing to prevent forgetting - 2023-02arXiv 2302.06600Task-Specific Skill Localization in Fine-tuned Language Models
Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao et al. · Language models & NLP
Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-shot settings. Thus fine-tuning allows the model to quickly pick up task-specific ``skills,'' but there has been limited study of where these newly-learnt skills reside inside the massive model.
- 2023-01arXiv 2301.12131Restricted Orthogonal Gradient Projection for Continual Learning
Zeyuan Yang, Zonghan Yang, Peng Li et al. · Machine learning
Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge.
- 2023-01arXiv 2301.04213Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Peter Hase, Mohit Bansal, Been Kim et al. · Machine learning
Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights.
- 2022-10arXiv 2210.11466Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
Yoonho Lee, Annie S. Chen, Fahim Tajwar et al. · Machine learning
A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task.
- 2020-10arXiv 2010.05874Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
Zirui Wang, Yulia Tsvetkov, Orhan Firat et al. · Language models & NLP
Massively multilingual models subsuming tens or even hundreds of languages pose great challenges to multi-task optimization.
- 2020-01arXiv 2001.06782Gradient Surgery for Multi-Task Learning
Tianhe Yu, Saurabh Kumar, Abhishek Gupta et al. · Machine learning
While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge.
Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.
