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.
- 2025-06arXiv 2506.10139Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Arushi Somani et al. · Language models & NLP
To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabilities, it is difficult or impossible to get high-quality human supervision.
- 2025-06arXiv 2506.08920PropMEND: Hypernetworks for Knowledge Propagation in LLMs
Zeyu Leo Liu, Greg Durrett, Eunsol Choi · Language models & NLP
Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the injected knowledge.
- 2025-06arXiv 2506.00823Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
Yuntai Bao, Xuhong Zhang, Tianyu Du et al. · Language models & NLP
Large language models (LLMs) are trained on extensive datasets that encapsulate substantial world knowledge. However, their outputs often include confidently stated inaccuracies.
- 2025-05arXiv 2505.23295How Does Response Length Affect Long-Form Factuality
James Xu Zhao, Jimmy Z. J. Liu, Bryan Hooi et al. · Language models & NLP
Large language models (LLMs) are widely used for long-form text generation. However, factual errors in the responses would undermine their reliability. Despite growing attention to LLM factuality, the effect of response length on factuality remains underexplored.
- 2025-05arXiv 2505.22631GPU-Accelerated Simulated Oscillator Ising/Potts Machine Solving Combinatorial Optimization Problems
Yilmaz Ege Gonul, Ceyhun Efe Kayan, Ilknur Mustafazade et al. · Hardware, photonics & physics
Oscillator-based Ising machines (OIMs) and oscillator-based Potts machines (OPMs) have emerged as promising hardware accelerators for solving NP-hard combinatorial optimization problems by leveraging the phase dynamics of coupled oscillators.
- 2025-05arXiv 2505.21444Can Large Reasoning Models Self-Train?
Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov et al. · Machine learning
Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL.
- 2025-05arXiv 2505.19106An Ultra-Low Power and Fast Ising Machine using Voltage-Controlled Magnetoresistive Random Access Memory
Sai Li, Yihao Zhang, Albert Lee et al. · Hardware, photonics & physics
Physics-inspired computing paradigms, such as Ising machines, are emerging as promising hardware alternatives to traditional von Neumann architectures for tackling computationally intensive combinatorial optimization problems (COPs).
- 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 2505.17126Conformal 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 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 2505.13252A 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 2505.00979Synthesize-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.
- 2025-04arXiv 2504.13171Sleep-time Compute: Beyond Inference Scaling at Test-time
Kevin Lin, Charlie Snell, Yu Wang et al. · AI & agents
Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost.
- 2025-03arXiv 2503.18866Reasoning to Learn from Latent Thoughts
Yangjun Ruan, Neil Band, Chris J. Maddison et al. · Machine learning
Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling.
- 2025-03arXiv 2503.15427Direct comparison of stochastic driven nonlinear dynamical systems for combinatorial optimization
Junpeng Hou, Amin Barzegar, Helmut G. Katzgraber · Phys. Rev. E 112, 035301 (2025) · Hardware, photonics & physics
Combinatorial optimization problems are ubiquitous in industrial applications. However, finding optimal or close-to-optimal solutions can often be extremely hard.
- 2025-03arXiv 2503.05683WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
Lukas Thede, Karsten Roth, Matthias Bethge et al. · Language models & NLP
Keeping large language models factually up-to-date is crucial for deployment, yet costly retraining remains a challenge. Knowledge editing offers a promising alternative, but methods are only tested on small-scale or synthetic edit benchmarks.
Cited inEWC protects what its Fisher sees: a literature synthesis on elastic weight consolidation, scale and coherenceStudy: Consequence consistent updatesStudy: Continual learning order and companion dataStudy: Elastic weight consolidation deep diveStudy: Fortifying knowledge in continual learningStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesisStudy: Weight editing to prevent forgetting - 2025-02arXiv 2502.17416Reasoning with Latent Thoughts: On the Power of Looped Transformers
Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li et al. · Language models & NLP
Large language models have shown remarkable reasoning abilities and scaling laws suggest that large parameter count, especially along the depth axis, is the primary driver.
- 2025-02arXiv 2502.15652Empowering LLMs with Logical Reasoning: A Comprehensive Survey
Fengxiang Cheng, Haoxuan Li, Fenrong Liu et al. · AI & agents
Large language models (LLMs) have achieved remarkable successes on various tasks.
- 2025-02arXiv 2502.15924Improving Consistency in Large Language Models through Chain of Guidance
Harsh Raj, Vipul Gupta, Domenic Rosati et al. · Language models & NLP
Consistency is a fundamental dimension of trustworthiness in Large Language Models (LLMs). For humans to be able to trust LLM-based applications, their outputs should be consistent when prompted with inputs that carry the same meaning or intent.
- 2025-02arXiv 2502.05171Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Jonas Geiping, Sean McLeish, Neel Jain et al. · Machine learning
We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent block, thereby unrolling to arbitrary depth at test-time.
- 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.
- 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 2412.16100Logical 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.
- 2024-12arXiv 2412.06538Understanding Factual Recall in Transformers via Associative Memories
Eshaan Nichani, Jason D. Lee, Alberto Bietti · Machine learning
Large language models have demonstrated an impressive ability to perform factual recall. Prior work has found that transformers trained on factual recall tasks can store information at a rate proportional to their parameter count.
- 2024-10arXiv 2410.16713Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World
Joshua Kazdan, Rylan Schaeffer, Apratim Dey et al. · Machine learning
What happens when generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models? collapse can be avoided) by managing how available data are used in pretraining.
- 2024-10arXiv 2410.08047Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
Hyun Ryu, Gyeongman Kim, Hyemin S. Lee et al. · The Thirteenth International Conference on Learning Representations (ICLR 2025) · Language models & NLP
Complex logical reasoning tasks require a long sequence of reasoning, which a large language model (LLM) with chain-of-thought prompting still falls short. To alleviate this issue, neurosymbolic approaches incorporate a symbolic solver.
- 2024-10arXiv 2410.02197Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
Yifan Zhang, Ge Zhang, Yue Wu et al. · AI & agents
Modeling human preferences is crucial for aligning foundation models with human values. Traditional reward modeling methods, such as the Bradley-Terry (BT) reward model, fall short in expressiveness, particularly in addressing intransitive preferences.
- 2024-09arXiv 2409.16636Training Language Models to Win Debates with Self-Play Improves Judge Accuracy
Samuel Arnesen, David Rein, Julian Michael · Language models & NLP
We test the robustness of debate as a method of scalable oversight by training models to debate with data generated via self-play. In a long-context reading comprehension task, we find that language model based evaluators answer questions more accurately when judging models optimized to win debates.
- 2024-09arXiv 2409.16461Strategies for Improving NL-to-FOL Translation with LLMs: Data Generation, Incremental Fine-Tuning, and Verification
Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine et al. · Language models & NLP
Logical reasoning is a fundamental task in natural language processing that presents significant challenges to Large Language Models (LLMs). The inherent characteristics of logical reasoning makes it well-suited for symbolic representations such as first-order logic (FOL).
- 2024-09arXiv 2409.07431Synthetic continued pretraining
Zitong Yang, Neil Band, Shuangping Li et al. · Machine learning
Pretraining on large-scale, unstructured internet text enables language models to acquire a significant amount of world knowledge. However, this knowledge acquisition is data-inefficient--to learn a given fact, models must be trained on hundreds to thousands of diverse representations of it.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsStudy: Continual learning order and companion dataStudy: Generational competitive continual learningStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesis - 2024-09arXiv 2409.13724Logically Consistent Language Models via Neuro-Symbolic Integration
Diego Calanzone, Stefano Teso, Antonio Vergari · Language models & NLP
Large language models (LLMs) are a promising venue for natural language understanding and generation.
- 2024-07arXiv 2407.10490Learning Dynamics of LLM Finetuning
Yi Ren, Danica J. Sutherland · Machine learning
Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems.
- 2024-07arXiv 2407.12831Truth is Universal: Robust Detection of Lies in LLMs
Lennart Bürger, Fred A. Hamprecht, Boaz Nadler · Language models & NLP
Large Language Models (LLMs) have revolutionised natural language processing, exhibiting impressive human-like capabilities. In particular, LLMs are capable of "lying", knowingly outputting false statements.
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 - 2024-07arXiv 2407.12828Why Does New Knowledge Create Messy Ripple Effects in LLMs?
Jiaxin Qin, Zixuan Zhang, Manling Li et al. · Language models & NLP
Extensive previous research has focused on post-training knowledge editing (KE) for language models (LMs) to ensure that knowledge remains accurate and up-to-date.
Cited inA gradient kernel flags contradictions but does not predict forgetting, and steering rehearsal by it backfiresCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsEWC protects what its Fisher sees: a literature synthesis on elastic weight consolidation, scale and coherenceStudy: Elastic weight consolidation deep diveStudy: Logical coherence of LLM world models - 2024-06arXiv 2406.19764Belief Revision: The Adaptability of Large Language Models Reasoning
Bryan Wilie, Samuel Cahyawijaya, Etsuko Ishii et al. · Language models & NLP
The capability to reason from text is crucial for real-world NLP applications. Real-world scenarios often involve incomplete or evolving data. In response, individuals update their beliefs and understandings accordingly.
- 2024-06arXiv 2406.19276VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation
Yixiao Song, Yekyung Kim, Mohit Iyyer · Language models & NLP
, 2024), decompose an input text into "atomic claims" and verify each against a knowledge base like Wikipedia., can plausibly be proven true or false). We address this issue with VERISCORE, a metric for diverse long-form generation tasks that contain both verifiable and unverifiable content.
- 2024-06arXiv 2406.19354Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?
Peter Hase, Thomas Hofweber, Xiang Zhou et al. · Language models & NLP
The model editing problem concerns how language models should learn new facts about the world over time.
- 2024-06arXiv 2406.15927Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
Jannik Kossen, Jiatong Han, Muhammed Razzak et al. · Language models & NLP
We propose semantic entropy probes (SEPs), a cheap and reliable method for uncertainty quantification in Large Language Models (LLMs). Hallucinations, which are plausible-sounding but factually incorrect and arbitrary model generations, present a major challenge to the practical adoption of LLMs.
Cited inStable wrong beliefs evade every self-check: a literature synthesis on model self-knowledge and confident errorsStudy: Decision signatures for conflict detectionStudy: Logical coherence of LLM world modelsStudy: Model self knowledge and confident errorsStudy: Stopping confident wrong expert votes
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.
