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.
- 2025-05arXiv 2505.17762Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
Ziyu Ge, Yuhao Wu, Daniel Wai Kit Chin et al. · Language models & NLP
Large Language Models (LLMs) augmented with retrieval mechanisms have demonstrated significant potential in fact-checking tasks by integrating external knowledge.
- 2025-05arXiv 2505.18000Anytime-valid, Bayes-assisted, Prediction-Powered Inference
Valentin Kilian, Stefano Cortinovis, François Caron · Machine learning
Given a large pool of unlabelled data and a smaller amount of labels, prediction-powered inference (PPI) leverages machine learning predictions to increase the statistical efficiency of confidence interval procedures based solely on labelled data, while preserving fixed-time validity.
Cited inInternal notes - 2025-05arXiv 2505.16170When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction
Yuqing Yang, Robin Jia · Language models & NLP
, spontaneously and immediately acknowledge errors in their previously generated false assertions. Using model-specific testbeds, we find that while LLMs are capable of retraction, they do so only rarely, even when they can recognize their mistakes when asked in a separate interaction.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStable wrong beliefs evade every self-check: a literature synthesis on model self-knowledge and confident errorsStudy: Logical coherence of LLM world modelsStudy: Model self knowledge and confident errors - 2025-05arXiv 2505.16831Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Xiaoyu Xu, Xiang Yue, Yang Liu et al. · Language models & NLP
Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity.
- 2025-05arXiv 2505.15424Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models
Yan-Shuo Liang, Jia-Rui Chen, Wu-Jun Li · Language models & NLP
Continual learning (CL), which requires the model to learn multiple tasks sequentially, is crucial for large language models (LLMs). Recently, low-rank adaptation~(LoRA), one of the most representative parameter-efficient fine-tuning (PEFT) methods, has gained increasing attention in CL of LLMs.
- 2025-05arXiv 2505.16037Causal LLM Routing: End-to-End Regret Minimization from Observational Data
Asterios Tsiourvas, Wei Sun, Georgia Perakis · AI & agents
LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models.
- 2025-05arXiv 2505.17126Conformal Language Model Reasoning with Coherent Factuality
Maxon Rubin-Toles, Maya Gambhir, Keshav Ramji et al. · Language models & NLP
Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStable wrong beliefs evade every self-check: a literature synthesis on model self-knowledge and confident errorsStudy: Logical coherence of LLM world modelsStudy: Model self knowledge and confident errors - 2025-05arXiv 2506.11038MoTE: Mixture of Task-specific Experts for Pre-Trained ModelBased Class-incremental Learning
Linjie Li, Zhenyu Wu, Yang Ji · Machine learning
Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information.
- 2025-05arXiv 2505.13988The Hallucination Tax of Reinforcement Finetuning
Linxin Song, Taiwei Shi, Jieyu Zhao · Language models & NLP
Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness remains underexplored.
- 2025-05arXiv 2505.14173THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation
Yunlong Liang, Fandong Meng, Jie Zhou · Language models & NLP
The sparse Mixture-of-Experts (MoE) has achieved significant progress for neural machine translation (NMT).
- 2025-05arXiv 2505.14489Reasoning Models Better Express Their Confidence
Dongkeun Yoon, Seungone Kim, Sohee Yang et al. · AI & agents
Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability.
- 2025-05arXiv 2505.14625TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Zhangchen Xu, Yuetai Li, Fengqing Jiang et al. · Machine learning
Reinforcement Learning (RL) has become a powerful tool for enhancing the reasoning abilities of large language models (LLMs) by optimizing their policies with reward signals.
- 2025-05arXiv 2505.14679UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
Xiaojie Gu, Ziying Huang, Jia-Chen Gu et al. · Language models & NLP
Lifelong learning enables large language models (LLMs) to adapt to evolving information by continually updating their internal knowledge. An ideal system should support efficient, wide-ranging updates while preserving existing capabilities and ensuring reliable deployment.
- 2025-05arXiv 2505.12601Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
Yang Li · Machine learning
As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for efficient and effective deployment.
- 2025-05arXiv 2505.13252A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems
Rikhil Amonkar, Ceyhun Efe Kayan, Qimei Lai et al. · Language models & NLP
Recent work shows superior performance when using large language models (LLMs) as formalizers instead of as end-to-end solvers for symbolic reasoning problems. Given the problem description, the LLM generates a formal program that derives a solution via an external solver.
- 2025-05arXiv 2505.12512Scalable Strategies for Continual Learning with Replay
Truman Hickok · Machine learning
Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference.
- 2025-05arXiv 2505.11816Continuous Subspace Optimization for Continual Learning
Quan Cheng, Yuanyu Wan, Lingyu Wu et al. · Vision
Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks.
- 2025-05arXiv 2505.11831ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
Francois Chollet, Mike Knoop, Gregory Kamradt et al. · AI & agents
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI), introduced in 2019, established a challenging benchmark for evaluating the general fluid intelligence of artificial systems via a set of unique, novel tasks only requiring minimal prior knowledge.
Cited inStudy: Superintelligence - 2025-05arXiv 2505.11876EAMET: Robust Massive Model Editing via Embedding Alignment Optimization
Yanbo Dai, Zhenlan Ji, Zongjie Li et al. · Language models & NLP
Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical metrics.
- 2025-05arXiv 2505.11883MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
Zihuan Qiu, Yi Xu, Chiyuan He et al. · Machine learning
Continual model merging integrates independently fine-tuned models sequentially without access to the original training data, offering a scalable and efficient solution for continual learning.
- 2025-05arXiv 2505.10833MergeBench: A Benchmark for Merging Domain-Specialized LLMs
Yifei He, Siqi Zeng, Yuzheng Hu et al. · Machine learning
Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data.
- 2025-05arXiv 2505.11329TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference
Raja Gond, Nipun Kwatra, Ramachandran Ramjee · Other
Distributed inference of large language models (LLMs) using tensor parallelism can introduce communication overheads of $20$% even over GPUs connected via NVLink, a high-speed GPU interconnect.
Cited inThe Wrong Phase - 2025-05arXiv 2505.09343Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures
Chenggang Zhao, Chengqi Deng, Chong Ruan et al. · Proceedings of the 52nd Annual International Symposium on Computer Architecture (ISCA '25), June 2025 · Other
The rapid scaling of large language models (LLMs) has unveiled critical limitations in current hardware architectures, including constraints in memory capacity, computational efficiency, and interconnection bandwidth.
Cited inThe Wrong Phase - 2025-05arXiv 2505.09388Qwen3 Technical Report
An Yang, Anfeng Li, Baosong Yang et al. · Language models & NLP
In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities.
- 2025-05arXiv 2505.09663Analog Foundation Models
Julian Büchel, Iason Chalas, Giovanni Acampa et al. · Machine learning
Analog in-memory computing (AIMC) is a promising compute paradigm to improve speed and power efficiency of neural network inference beyond the limits of conventional von Neumann-based architectures.
Cited inThe Wrong Phase - 2025-05arXiv 2505.05946Full-Parameter Continual Pretraining of Gemma2: Insights into Fluency and Domain Knowledge
Vytenis Šliogeris, Povilas Daniušis, Artūras Nakvosas · Language models & NLP
In this technical report, we empirically investigate the relationship between linguistic fluency and domain knowledge in the context of continual learning with large language models (LLMs).
- 2025-05arXiv 2505.05017Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization
Yuntai Bao, Xuhong Zhang, Tianyu Du et al. · Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence Main Track (2025) 8022-8030 · Language models & NLP
Pre-trained large language models (LLMs) are commonly fine-tuned to adapt to downstream tasks. Since the majority of knowledge is acquired during pre-training, attributing the predictions of fine-tuned LLMs to their pre-training data may provide valuable insights.
- 2025-05arXiv 2505.03275RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
Tiantian Gan, Qiyao Sun · AI & agents
Large language models (LLMs) struggle to effectively utilize a growing number of external tools, such as those defined by the Model Context Protocol (MCP)\cite{IntroducingMCP}, due to prompt bloat and selection complexity.
- 2025-05arXiv 2505.03335Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Yang Yue et al. · Machine learning
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards.
- 2025-05arXiv 2505.02486SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
Jinpeng Chen, Runmin Cong, Yuzhi Zhao et al. · Machine learning
Multimodal Continual Instruction Tuning (MCIT) aims to enable Multimodal Large Language Models (MLLMs) to incrementally learn new tasks without catastrophic forgetting.
Cited inInternal notes - 2025-05arXiv 2505.00979Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models
Shengjie Ma, Xuhui Jiang, Chengjin Xu et al. · Language models & NLP
Large Language Models (LLMs) have achieved remarkable success but remain data-inefficient, especially when learning from small, specialized corpora with limited and proprietary data.
- 2025-05arXiv 2505.00268Consistency in Language Models: Current Landscape, Challenges, and Future Directions
Jekaterina Novikova, Carol Anderson, Borhane Blili-Hamelin et al. · Language models & NLP
The hallmark of effective language use lies in consistency: expressing similar meanings in similar contexts and avoiding contradictions.
- 2025-05arXiv 2505.00843OET: Optimization-based prompt injection Evaluation Toolkit
Jinsheng Pan, Xiaogeng Liu, Chaowei Xiao · Security
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains.
- 2025-04arXiv 2505.00212Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Shaokun Zhang, Ming Yin, Jieyu Zhang et al. · AI & agents
Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive.
Cited inInternal notes - 2025-04arXiv 2504.20879The Leaderboard Illusion
Shivalika Singh, Yiyang Nan, Alex Wang et al. · AI & agents
Measuring progress is fundamental to the advancement of any scientific field. As benchmarks play an increasingly central role, they also grow more susceptible to distortion.
- 2025-04arXiv 2504.19413Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Prateek Chhikara, Dev Khant, Saket Aryan et al. · Language models & NLP
Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues.
Cited inStudy: Graphyte spec - 2025-04arXiv 2504.19622From Evidence to Belief: A Bayesian Epistemology Approach to Language Models
Minsu Kim, Sangryul Kim, James Thorne · AI & agents
This paper investigates the knowledge of language models from the perspective of Bayesian epistemology. We explore how language models adjust their confidence and responses when presented with evidence with varying levels of informativeness and reliability.
- 2025-04arXiv 2504.18530Scaling Laws For Scalable Oversight
Joshua Engels, David D. Baek, Subhash Kantamneni et al. · NeurIPS 2025 (Spotlight) · AI & agents
Scalable oversight, the process by which weaker AI systems supervise stronger ones, has been proposed as a key strategy to control future superintelligent systems.
- 2025-04arXiv 2504.17550HalluLens: LLM Hallucination Benchmark
Yejin Bang, Ziwei Ji, Alan Schelten et al. · Language models & NLP
" These hallucinations undermine user trust and hinder the adoption of generative AI systems. Addressing hallucinations is essential for the advancement of LLMs.
- 2025-04arXiv 2504.15228A Self-Improving Coding Agent
Maxime Robeyns, Martin Szummer, Laurence Aitchison · AI & agents
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools.
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.
