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.
- 2023-11arXiv 2311.09603Self-Contradictory Reasoning Evaluation and Detection
Ziyi Liu, Soumya Sanyal, Isabelle Lee et al. · Language models & NLP
In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks only focus on final answers.
- 2023-11arXiv 2311.09677R-Tuning: Instructing Large Language Models to Say `I Don't Know'
Hanning Zhang, Shizhe Diao, Yong Lin et al. · Language models & NLP
Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed hallucination.
- 2023-11arXiv 2311.08702Debate Helps Supervise Unreliable Experts
Julian Michael, Salsabila Mahdi, David Rein et al. · AI & agents
As AI systems are used to answer more difficult questions and potentially help create new knowledge, judging the truthfulness of their outputs becomes more difficult and more important.
- 2023-11arXiv 2311.08718Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
Bairu Hou, Yujian Liu, Kaizhi Qian et al. · Language models & NLP
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty, resulting from missing information in the model's training data.
- 2023-11arXiv 2311.10770Exponentially Faster Language Modelling
Peter Belcak, Roger Wattenhofer · Language models & NLP
Language models only really need to use an exponential fraction of their neurons for individual inferences.3% of its neurons during inference while performing on par with similar BERT models.
- 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 2311.08106Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models
Yujin Kim, Jaehong Yoon, Seonghyeon Ye et al. · Language models & NLP
The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquiring new knowledge but also overwriting outdated information into updated ones.
- 2023-11arXiv 2311.08401Fine-tuning Language Models for Factuality
Katherine Tian, Eric Mitchell, Huaxiu Yao et al. · Language models & NLP
The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines.
- 2023-11arXiv 2311.08516LLMs cannot find reasoning errors, but can correct them given the error location
Gladys Tyen, Hassan Mansoor, Victor Cărbune et al. · AI & agents
g., 2023). In this paper, we show that poor self-correction performance stems from LLMs' inability to find logical mistakes, rather than their ability to correct a known mistake.
- 2023-11arXiv 2311.08596Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment
Philippe Laban, Lidiya Murakhovs'ka, Caiming Xiong et al. · Language models & NLP
The interactive nature of Large Language Models (LLMs) theoretically allows models to refine and improve their answers, yet systematic analysis of the multi-turn behavior of LLMs remains limited.
- 2023-11arXiv 2311.07383LM-Polygraph: Uncertainty Estimation for Language Models
Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun et al. · Language models & NLP
Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields., fabricate facts without providing users an apparent means to discern the veracity of their statements.
- 2023-11arXiv 2311.06305A Systematic Review on Fostering Appropriate Trust in Human-AI Interaction
Siddharth Mehrotra, Chadha Degachi, Oleksandra Vereschak et al. · Society, software & economics
Appropriate Trust in Artificial Intelligence (AI) systems has rapidly become an important area of focus for both researchers and practitioners. Various approaches have been used to achieve it, such as confidence scores, explanations, trustworthiness cues, or uncertainty communication.
- 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.
- 2023-11arXiv 2311.02462Levels of AGI for Operationalizing Progress on the Path to AGI
Meredith Ringel Morris, Jascha Sohl-Dickstein, Noah Fiedel et al. · Proceedings of ICML 2024 · AI & agents
We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors.
- 2023-11arXiv 2311.01453PPI++: Efficient Prediction-Powered Inference
Anastasios N. Angelopoulos, John C. Duchi, Tijana Zrnic · Machine learning
We present PPI++: a computationally lightweight methodology for estimation and inference based on a small labeled dataset and a typically much larger dataset of machine-learning predictions.
- 2023-10arXiv 2310.20624LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish · Machine learning
AI developers often apply safety alignment procedures to prevent the misuse of their AI systems.
- 2023-10arXiv 2310.15910Characterizing Mechanisms for Factual Recall in Language Models
Qinan Yu, Jack Merullo, Ellie Pavlick · Language models & NLP
Language Models (LMs) often must integrate facts they memorized in pretraining with new information that appears in a given context. These two sources can disagree, causing competition within the model, and it is unclear how an LM will resolve the conflict.
- 2023-10arXiv 2310.16046A Unified, Scalable Framework for Neural Population Decoding
Mehdi Azabou, Vinam Arora, Venkataramana Ganesh et al. · Machine learning
Our ability to use deep learning approaches to decipher neural activity would likely benefit from greater scale, in terms of both model size and datasets.
- 2023-10arXiv 2310.16226TiC-CLIP: Continual Training of CLIP Models
Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari et al. · Vision
Keeping large foundation models up to date on latest data is inherently expensive. To avoid the prohibitive costs of constantly retraining, it is imperative to continually train these models.
- 2023-10arXiv 2310.15164LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
Theo X. Olausson, Alex Gu, Benjamin Lipkin et al. · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5153-5176, Singapore. Association for Computational Linguistics · Language models & NLP
, deductively inferring the truth value of a conclusion from a set of premises, is an important task for artificial intelligence with wide potential impacts on science, mathematics, and society.
- 2023-10arXiv 2310.14152Orthogonal Subspace Learning for Language Model Continual Learning
Xiao Wang, Tianze Chen, Qiming Ge et al. · Language models & NLP
Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their performance degrades in scenarios where multiple tasks are encountered sequentially, also known as catastrophic forgetting.
Cited inEWC protects what its Fisher sees: a literature synthesis on elastic weight consolidation, scale and coherenceStudy: Continual learning order and companion dataStudy: Elastic weight consolidation deep diveStudy: Fortifying knowledge in continual learningStudy: Genesys program prior artStudy: Hardware guardian core for continual learningStudy: Merging and splitting MoE expertsStudy: Orchestrated specialists and bridge synthesisStudy: Seven continual learning methods tested - 2023-10arXiv 2310.13548Towards Understanding Sycophancy in Language Models
Mrinank Sharma, Meg Tong, Tomasz Korbak et al. · Language models & NLP
Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy.
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 - 2023-10arXiv 2310.13798Specific versus General Principles for Constitutional AI
Sandipan Kundu, Yuntao Bai, Saurav Kadavath et al. · Language models & NLP
Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-preservation or power.
- 2023-10arXiv 2310.12962An Emulator for Fine-Tuning Large Language Models using Small Language Models
Eric Mitchell, Rafael Rafailov, Archit Sharma et al. · Language models & NLP
Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted examples or other specifications of desired behaviors.
- 2023-10arXiv 2310.12963AutoMix: Automatically Mixing Language Models
Pranjal Aggarwal, Aman Madaan, Ankit Anand et al. · Language models & NLP
Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and performance remains challenging.
- 2023-10arXiv 2310.11511Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Akari Asai, Zeqiu Wu, Yizhong Wang et al. · Language models & NLP
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate.
- 2023-10arXiv 2310.10348Attribution Patching Outperforms Automated Circuit Discovery
Aaquib Syed, Can Rager, Arthur Conmy · Machine learning
Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models.
- 2023-10arXiv 2310.08540Do pretrained Transformers Learn In-Context by Gradient Descent?
Lingfeng Shen, Aayush Mishra, Daniel Khashabi · Language models & NLP
The emergence of In-Context Learning (ICL) in LLMs remains a remarkable phenomenon that is partially understood. To explain ICL, recent studies have created theoretical connections to Gradient Descent (GD).
- 2023-10arXiv 2310.07234Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Liyuan Wang, Jingyi Xie, Xingxing Zhang et al. · Machine learning
Prompt-based continual learning is an emerging direction in leveraging pre-trained knowledge for downstream continual learning, and has almost reached the performance pinnacle under supervised pre-training.
- 2023-10arXiv 2310.07923The Expressive Power of Transformers with Chain of Thought
William Merrill, Ashish Sabharwal · Machine learning
Recent theoretical work has identified surprisingly simple reasoning problems, such as checking if two nodes in a graph are connected or simulating finite-state machines, that are provably unsolvable by standard transformers that answer immediately after reading their input.
Cited inWhat Language Buys - 2023-10arXiv 2310.06272Let Models Speak Ciphers: Multiagent Debate through Embeddings
Chau Pham, Boyi Liu, Yingxiang Yang et al. · Language models & NLP
Discussion and debate among Large Language Models (LLMs) have gained considerable attention due to their potential to enhance the reasoning ability of LLMs.
- 2023-10arXiv 2310.06762TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
Xiao Wang, Yuansen Zhang, Tianze Chen et al. · Language models & NLP
Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked.
- 2023-10arXiv 2310.06770SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Carlos E. Jimenez, John Yang, Alexander Wettig et al. · Language models & NLP
Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities.
Cited inInternal notes - 2023-10arXiv 2310.06824The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Samuel Marks, Max Tegmark · AI & agents
Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM's internal activations.
- 2023-10arXiv 2310.07064Large Language Models can Learn Rules
Zhaocheng Zhu, Yuan Xue, Xinyun Chen et al. · AI & agents
When prompted with a few examples and intermediate steps, large language models (LLMs) have demonstrated impressive performance in various reasoning tasks.
- 2023-10arXiv 2310.05002Self-Knowledge Guided Retrieval Augmentation for Large Language Models
Yile Wang, Peng Li, Maosong Sun et al. · Language models & NLP
Large language models (LLMs) have shown superior performance without task-specific fine-tuning. Despite the success, the knowledge stored in the parameters of LLMs could still be incomplete and difficult to update due to the computational costs.
- 2023-10arXiv 2310.03693Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Xiangyu Qi, Yi Zeng, Tinghao Xie et al. · Language models & NLP
Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning.5 Turbo on custom datasets also encourage this practice.
- 2023-10arXiv 2310.02743Reward Model Ensembles Help Mitigate Overoptimization
Thomas Coste, Usman Anwar, Robert Kirk et al. · Machine learning
Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. As part of this process, learned reward models are used to approximately model human preferences.
Cited inWhen the Exploit Is Constructed - 2023-10arXiv 2310.02984Scaling Laws for Associative Memories
Vivien Cabannes, Elvis Dohmatob, Alberto Bietti · Machine learning
Learning arguably involves the discovery and memorization of abstract rules. The aim of this paper is to study associative memory mechanisms. Our model is based on high-dimensional matrices consisting of outer products of embeddings, which relates to the inner layers of transformer language models.
- 2023-10arXiv 2310.03128MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
Yue Huang, Jiawen Shi, Yuan Li et al. · Society, software & economics
Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs.
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.
