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.
- 2025-02arXiv 2502.03407Detecting Strategic Deception Using Linear Probes
Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim et al. · Machine learning
AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned.
- 2025-02arXiv 2502.03461Do Large Language Model Benchmarks Test Reliability?
Joshua Vendrow, Edward Vendrow, Sara Beery et al. · Machine learning
When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus on measuring their reliability.
- 2025-02arXiv 2502.04390In Praise of Stubbornness: An Empirical Case for Cognitive-Dissonance Aware Continual Update of Knowledge in LLMs
Simone Clemente, Zied Ben Houidi, Alexis Huet et al. · Language models & NLP
Through systematic empirical investigation, we uncover a fundamental and concerning property of Large Language Models: while they can safely learn facts that don't contradict their knowledge, attempting to update facts with contradictory information triggers catastrophic corruption of unrelated knowledge.
- 2025-02arXiv 2502.02671On Teacher Hacking in Language Model Distillation
Daniil Tiapkin, Daniele Calandriello, Johan Ferret et al. · Machine learning
Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where the LM is aligned by optimizing a reward model.
- 2025-02arXiv 2502.02737SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Loubna Ben Allal, Anton Lozhkov, Elie Bakouch et al. · Language models & NLP
While large language models have facilitated breakthroughs in many applications of artificial intelligence, their inherent largeness makes them computationally expensive and challenging to deploy in resource-constrained settings.
- 2025-02arXiv 2502.01534Preference Leakage: A Contamination Problem in LLM-as-a-judge
Dawei Li, Renliang Sun, Yue Huang et al. · Machine learning
Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods in model development.
- 2025-02arXiv 2502.01636Lifelong Knowledge Editing requires Better Regularization
Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu et al. · Language models & NLP
Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing.
- 2025-02arXiv 2502.05209Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk et al. · Security
Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system.
- 2025-02arXiv 2502.00674Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
Wenzhe Li, Yong Lin, Mengzhou Xia et al. · Language models & NLP
Ensembling outputs from diverse sources is a straightforward yet effective approach to boost performance. Mixture-of-Agents (MoA) is one such popular ensemble method that aggregates outputs from multiple different Large Language Models (LLMs).
- 2025-02arXiv 2502.00592M+: Extending MemoryLLM with Scalable Long-Term Memory
Yu Wang, Dmitry Krotov, Yuanzhe Hu et al. · Language models & NLP
Equipping large language models (LLMs) with latent-space memory has attracted increasing attention as they can extend the context window of existing language models.
- 2025-01arXiv 2501.18837Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu et al. · Language models & NLP
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes that require many model interactions, like manufacturing illegal substances at scale.
- 2025-01arXiv 2502.01657Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
Varun Dhanraj, Chris Eliasmith · Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 30577--30596 · Machine learning
Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical reasoning.
- 2025-01arXiv 2501.17703Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Yubo Wang, Xiang Yue, Wenhu Chen · Language models & NLP
Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks.
- 2025-01arXiv 2501.16946Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development
Jan Kulveit, Raymond Douglas, Nora Ammann et al. · Society, software & economics
This paper examines the systemic risks posed by incremental advancements in artificial intelligence, developing the concept of `gradual disempowerment', in contrast to the abrupt takeover scenarios commonly discussed in AI safety.
- 2025-01arXiv 2501.17148AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Zhengxuan Wu, Aryaman Arora, Atticus Geiger et al. · Language models & NLP
Fine-grained steering of language model outputs is essential for safety and reliability.
- 2025-01arXiv 2501.13453Spurious Forgetting in Continual Learning of Language Models
Junhao Zheng, Xidi Cai, Shengjie Qiu et al. · Machine learning
Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying knowledge retention.
- 2025-01arXiv 2501.13669How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization
Shezheng Song, Hao Xu, Jun Ma et al. · Language models & NLP
Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired during pretraining.
- 2025-01arXiv 2501.14082Communicating Activations Between Language Model Agents
Vignav Ramesh, Kenneth Li · Language models & NLP
Communication between multiple language model (LM) agents has been shown to scale up the reasoning ability of LMs.
- 2025-01arXiv 2501.12774LLMs as Repositories of Factual Knowledge: Limitations and Solutions
Seyed Mahed Mousavi, Simone Alghisi, Giuseppe Riccardi · Language models & NLP
). Such unstructured knowledge is subject to change due to updates through time from past to present. Equally important are the inconsistencies and inaccuracies occurring in different information sources.
- 2025-01arXiv 2501.12835Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
Viktor Moskvoretskii, Maria Lysyuk, Mikhail Salnikov et al. · Language models & NLP
Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs.
- 2025-01arXiv 2501.11587Recurrent Diffusion for Large-Scale Parameter Generation
Kai Wang, Dongwen Tang, Wangbo Zhao et al. · Machine learning
Parameter generation has long struggled to match the scale of today large vision and language models, curbing its broader utility.
- 2025-01arXiv 2501.13956Zep: A Temporal Knowledge Graph Architecture for Agent Memory
Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais et al. · Language models & NLP
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark.
Cited inStudy: Graphyte spec - 2025-01arXiv 2501.09038Do generative video models understand physical principles?
Saman Motamed, Laura Culp, Kevin Swersky et al. · Vision
AI video generation is undergoing a revolution, with quality and realism advancing rapidly.
- 2025-01arXiv 2501.04899SUGAR: Leveraging Contextual Confidence for Smarter Retrieval
Hanna Zubkova, Ji-Hoon Park, Seong-Whan Lee · Language models & NLP
Bearing in mind the limited parametric knowledge of Large Language Models (LLMs), retrieval-augmented generation (RAG) which supplies them with the relevant external knowledge has served as an approach to mitigate the issue of hallucinations to a certain extent.
- 2025-01arXiv 2501.03575Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Niket Agarwal et al. · Vision
Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups.
- 2025-01arXiv 2501.03905MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training
Xudong Liao, Yijun Sun, Han Tian et al. · Proceedings of the 2025 ACM SIGCOMM Conference · Other
Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named experts, on a per-token basis.
Cited inThe Wrong Phase - 2025-01arXiv 2501.01818Rerouting LLM Routers
Avital Shafran, Roei Schuster, Thomas Ristenpart et al. · Security
LLM routers aim to balance quality and cost of generation by classifying queries and routing them to a cheaper or more expensive LLM depending on their complexity.
- 2025-01arXiv 2501.01956Metadata Conditioning Accelerates Language Model Pre-training
Tianyu Gao, Alexander Wettig, Luxi He et al. · Language models & NLP
The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently learning and deploying the correct behaviors exemplified in each of these heterogeneous data sources is challenging.
- 2025-01arXiv 2501.00879TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
Huichi Zhou, Kin-Hei Lee, Zhonghao Zhan et al. · Language models & NLP
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries.
- 2024-12arXiv 2501.00663Titans: Learning to Memorize at Test Time
Ali Behrouz, Peilin Zhong, Vahab Mirrokni · Machine learning
Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention.
- 2024-12arXiv 2412.19437DeepSeek-V3 Technical Report
DeepSeek-AI, Aixin Liu, Bei Feng et al. · Language models & NLP
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
- 2024-12arXiv 2412.19512Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Hua Farn, Hsuan Su, Shachi H Kumar et al. · Language models & NLP
Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models.
- 2024-12arXiv 2412.19792InfAlign: Inference-aware language model alignment
Ananth Balashankar, Ziteng Sun, Jonathan Berant et al. · Machine learning
Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base model.
- 2024-12arXiv 2412.18544Consistency Checks for Language Model Forecasters
Daniel Paleka, Abhimanyu Pallavi Sudhir, Alejandro Alvarez et al. · Machine learning
Forecasting is a task that is difficult to evaluate: the ground truth can only be known in the future. Recent work showing LLM forecasters rapidly approaching human-level performance begs the question: how can we benchmark and evaluate these forecasters instantaneously?
- 2024-12arXiv 2412.17009Expert Routing with Synthetic Data for Continual Learning
Yewon Byun, Sanket Vaibhav Mehta, Saurabh Garg et al. · Machine learning
In many real-world settings, regulations and economic incentives permit the sharing of models but not data across institutional boundaries. In such scenarios, practitioners might hope to adapt models to new domains, without losing performance on previous domains (so-called catastrophic forgetting).
- 2024-12arXiv 2412.17188Hierarchically Gated Experts for Efficient Online Continual Learning
Kevin Luong, Michael Thielscher · Machine learning
Continual Learning models aim to learn a set of tasks under the constraint that the tasks arrive sequentially with no way to access data from previous tasks. The Online Continual Learning framework poses a further challenge where the tasks are unknown and instead the data arrives as a single stream.
- 2024-12arXiv 2412.15571Continual Learning Using a Kernel-Based Method Over Foundation Models
Saleh Momeni, Sahisnu Mazumder, Bing Liu · Machine learning
Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation (ICS).
- 2024-12arXiv 2412.15690Theory of Mixture-of-Experts for Mobile Edge Computing
Hongbo Li, Lingjie Duan · Machine learning
In mobile edge computing (MEC) networks, mobile users generate diverse machine learning tasks dynamically over time. These tasks are typically offloaded to the nearest available edge server, by considering communication and computational efficiency.
- 2024-12arXiv 2412.16100Logical Consistency of Large Language Models in Fact-checking
Bishwamittra Ghosh, Sarah Hasan, Naheed Anjum Arafat et al. · Language models & NLP
In recent years, large language models (LLMs) have demonstrated significant success in performing varied natural language tasks such as language translation, question-answering, summarizing, fact-checking, etc.
- 2024-12arXiv 2412.16339Deliberative Alignment: Reasoning Enables Safer Language Models
Melody Y. Guan, Manas Joglekar, Eric Wallace et al. · Language models & NLP
As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental 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.
