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.
- 2024-01arXiv 2401.12617The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model
Daniel Goldfarb, Itay Evron, Nir Weinberger et al. · Machine learning
In continual learning, catastrophic forgetting is affected by multiple aspects of the tasks. Previous works have analyzed separately how forgetting is affected by either task similarity or overparameterization.
- 2024-01arXiv 2401.09670DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
Yinmin Zhong, Shengyu Liu, Junda Chen et al. · Other
DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across all users and requests.
Cited inThe Last Hardware Flank - 2024-01arXiv 2401.10020Self-Rewarding Language Models
Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho et al. · Language models & NLP
We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal.
- 2024-01arXiv 2401.10191Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan et al. · Machine learning
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task.
- 2024-01arXiv 2401.08565Tuning Language Models by Proxy
Alisa Liu, Xiaochuang Han, Yizhong Wang et al. · Language models & NLP
Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these models has become increasingly resource-intensive, or impossible when model weights are private.
- 2024-01arXiv 2401.08574Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen et al. · Language models & NLP
While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipulable model of the world.
- 2024-01arXiv 2401.07453Model Editing at Scale leads to Gradual and Catastrophic Forgetting
Akshat Gupta, Anurag Rao, Gopala Anumanchipalli · Language models & NLP
Editing knowledge in large language models is an attractive capability to have which allows us to correct incorrectly learnt facts during pre-training, as well as update the model with an ever-growing list of new facts.
- 2024-01arXiv 2401.06730Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren et al. · Language models & NLP
As natural language becomes the default interface for human-AI interaction, there is a need for LMs to appropriately communicate uncertainties in downstream applications.
- 2024-01arXiv 2401.05605Scaling Laws for Forgetting When Fine-Tuning Large Language Models
Damjan Kalajdzievski · Language models & NLP
We study and quantify the problem of forgetting when fine-tuning pre-trained large language models (LLMs) on a downstream task. We find that parameter-efficient fine-tuning (PEFT) strategies, such as Low-Rank Adapters (LoRA), still suffer from catastrophic forgetting.
- 2024-01arXiv 2401.06066DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Damai Dai, Chengqi Deng, Chenggang Zhao et al. · Language models & NLP
In the era of large language models, Mixture-of-Experts (MoE) is a promising architecture for managing computational costs when scaling up model parameters. each expert acquires non-overlapping and focused knowledge.
- 2024-01arXiv 2401.06121TOFU: A Task of Fictitious Unlearning for LLMs
Pratyush Maini, Zhili Feng, Avi Schwarzschild et al. · Machine learning
Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns.
- 2024-01arXiv 2401.05566Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Evan Hubinger, Carson Denison, Jesse Mu et al. · Security
Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity.
- 2024-01arXiv 2401.04700Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma et al. · Language models & NLP
Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining.
- 2024-01arXiv 2401.04088Mixtral of Experts
Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux et al. · Machine learning
We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model. experts). For every token, at each layer, a router network selects two experts to process the current state and combine their outputs.
- 2024-01arXiv 2401.03408Escalation Risks from Language Models in Military and Diplomatic Decision-Making
Juan-Pablo Rivera, Gabriel Mukobi, Anka Reuel et al. · The 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT 24), June 3-6, 2024, Rio de Janeiro, Brazil · AI & agents
Governments are increasingly considering integrating autonomous AI agents in high-stakes military and foreign-policy decision-making, especially with the emergence of advanced generative AI models like GPT-4.
- 2024-01arXiv 2401.02843Thousands of AI Authors on the Future of AI
Katja Grace, Harlan Stewart, Julia Fabienne Sandkühler et al. · Journal of Artificial Intelligence Research 84:9 (2025) · Society, software & economics
In the largest survey of its kind, 2,778 researchers who had published in top-tier artificial intelligence (AI) venues gave predictions on the pace of AI progress and the nature and impacts of advanced AI systems The aggregate forecasts give at least a 50% chance of AI systems achieving several milestones by 2028,…
- 2024-01arXiv 2401.02415LLaMA Pro: Progressive LLaMA with Block Expansion
Chengyue Wu, Yukang Gan, Yixiao Ge et al. · Language models & NLP
, from LLaMA to CodeLLaMA. To this end, we propose a new post-pretraining method for LLMs with an expansion of Transformer blocks. We tune the expanded blocks using only new corpus, efficiently and effectively improving the model's knowledge without catastrophic forgetting.
- 2024-01arXiv 2401.02509Memory, Consciousness and Large Language Model
Jitang Li, Jinzheng Li · Neuroscience & neural computation
With the development in cognitive science and Large Language Models (LLMs), increasing connections have come to light between these two distinct fields. Building upon these connections, we propose a conjecture suggesting the existence of a duality between LLMs and Tulving's theory of memory.
- 2024-01arXiv 2401.01286A Comprehensive Study of Knowledge Editing for Large Language Models
Ningyu Zhang, Yunzhi Yao, Bozhong Tian et al. · Language models & NLP
Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training, arising from their extensive parameterization.
- 2024-01arXiv 2401.01335Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Zixiang Chen, Yihe Deng, Huizhuo Yuan et al. · Machine learning
Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the prospect of growing a strong LLM out of a weak one without the need for acquiring additional human-annotated data.
- 2024-01arXiv 2401.00757LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
Yuxuan Wan, Wenxuan Wang, Yiliu Yang et al. · Society, software & economics
We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4.
- 2023-12arXiv 2312.15166SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
Dahyun Kim, Chanjun Park, Sanghoon Kim et al. · Language models & NLP
7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. Inspired by recent efforts to efficiently up-scale LLMs, we present a method for scaling LLMs called depth up-scaling (DUS), which encompasses depthwise scaling and continued pretraining.
- 2023-12arXiv 2312.09979LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
Shihan Dou, Enyu Zhou, Yan Liu et al. · Language models & NLP
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
- 2023-12arXiv 2312.10029Challenges with unsupervised LLM knowledge discovery
Sebastian Farquhar, Vikrant Varma, Zachary Kenton et al. · Machine learning
We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent.
- 2023-12arXiv 2312.09244Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking
Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal et al. · Machine learning
Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a phenomenon often termed \emph{reward hacking}.
- 2023-12arXiv 2312.09390Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner et al. · Language models & NLP
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated safe outputs.
- 2023-12arXiv 2312.06942AI Control: Improving Safety Despite Intentional Subversion
Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan et al. · Machine learning
As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes.
- 2023-12arXiv 2312.07000Alignment for Honesty
Yuqing Yang, Ethan Chern, Xipeng Qiu et al. · Language models & NLP
Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness.
- 2023-12arXiv 2312.06585Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Avi Singh, John D. Co-Reyes, Rishabh Agarwal et al. · Machine learning
Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of high-quality human data.
- 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 2312.05934Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
Oded Ovadia, Menachem Brief, Moshik Mishaeli et al. · AI & agents
Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains.
- 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.
- 2023-12arXiv 2401.08623Wake-Sleep Consolidated Learning
Amelia Sorrenti, Giovanni Bellitto, Federica Proietto Salanitri et al. · Neuroscience & neural computation
We propose Wake-Sleep Consolidated Learning (WSCL), a learning strategy leveraging Complementary Learning System theory and the wake-sleep phases of the human brain to improve the performance of deep neural networks for visual classification tasks in continual learning settings.
- 2023-12arXiv 2312.01188Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learning
Soumya Roy, Vinay K Verma, Deepak Gupta · Machine learning
This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared parameter.
- 2023-11arXiv 2311.17311Universal Self-Consistency for Large Language Model Generation
Xinyun Chen, Renat Aksitov, Uri Alon et al. · Language models & NLP
Self-consistency with chain-of-thought prompting (CoT) has demonstrated remarkable performance gains on various challenging tasks, by utilizing multiple reasoning paths sampled from large language models (LLMs).
- 2023-11arXiv 2311.17371Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
Andries Smit, Paul Duckworth, Nathan Grinsztajn et al. · Language models & NLP
Recent advancements in large language models (LLMs) underscore their potential for responding to inquiries in various domains. However, ensuring that generative agents provide accurate and reliable answers remains an ongoing challenge.
- 2023-11arXiv 2311.16452Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
Harsha Nori, Yin Tat Lee, Sheng Zhang et al. · Language models & NLP
Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot match specialist capabilities of fine-tuned models.
- 2023-11arXiv 2312.08748All-to-all reconfigurability with sparse and higher-order Ising machines
Srijan Nikhar, Sidharth Kannan, Navid Anjum Aadit et al. · Nature Communications (2024) · Other
Domain-specific hardware to solve computationally hard optimization problems has generated tremendous excitement. Here, we evaluate probabilistic bit (p-bit) based Ising Machines (IM) on the 3-regular 3-Exclusive OR Satisfiability (3R3X), as a representative hard optimization problem.
- 2023-11arXiv 2311.12022GPQA: A Graduate-Level Google-Proof Q&A Benchmark
David Rein, Betty Li Hou, Asa Cooper Stickland et al. · AI & agents
We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry., the questions are "Google-proof").
Cited inStudy: Superintelligence - 2023-11arXiv 2311.09476ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
Jon Saad-Falcon, Omar Khattab, Christopher Potts et al. · Language models & NLP
Evaluating retrieval-augmented generation (RAG) systems traditionally relies on hand annotations for input queries, passages to retrieve, and responses to generate.
Cited inInternal notes
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.
