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.
- 2023-06arXiv 2306.00802Birth of a Transformer: A Memory Viewpoint
Alberto Bietti, Vivien Cabannes, Diane Bouchacourt et al. · Machine learning
Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.
- 2023-05arXiv 2305.20050Let's Verify Step by Step
Hunter Lightman, Vineet Kosaraju, Yura Burda et al. · Machine learning
In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state-of-the-art models still regularly produce logical mistakes.
- 2023-05arXiv 2305.15852Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Niels Mündler, Jingxuan He, Slobodan Jenko et al. · Language models & NLP
Large language models (large LMs) are susceptible to producing text that contains hallucinated content. An important instance of this problem is self-contradiction, where the LM generates two contradictory sentences within the same context.
- 2023-05arXiv 2305.14795MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning et al. · Language models & NLP
The information stored in large language models (LLMs) falls out of date quickly, and retraining from scratch is often not an option. This has recently given rise to a range of techniques for injecting new facts through updating model weights.
Cited inTrust the premises, not the confidence: which belief to drop when an LLM contradicts itself, and why the solver is not the bottleneckStudy: Consequence consistent updatesStudy: Continual learning order and companion dataStudy: Graded succession by earned authorityStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesisStudy: Weight editing to prevent forgetting - 2023-05arXiv 2305.14250Language Models with Rationality
Nora Kassner, Oyvind Tafjord, Ashish Sabharwal et al. · Language models & NLP
While large language models (LLMs) are proficient at question-answering (QA), it is not always clear how (or even if) an answer follows from their latent "beliefs".
- 2023-05arXiv 2305.14251FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
Sewon Min, Kalpesh Krishna, Xinxi Lyu et al. · Language models & NLP
Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate, and (2) human evaluation is time-consuming and costly.
- 2023-05arXiv 2305.14325Improving Factuality and Reasoning in Language Models through Multiagent Debate
Yilun Du, Shuang Li, Antonio Torralba et al. · Language models & NLP
Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years.
- 2023-05arXiv 2305.12766Understanding Emergent In-Context Learning from a Kernel Regression Perspective
Chi Han, Ziqi Wang, Han Zhao et al. · Language models & NLP
Large language models (LLMs) have initiated a paradigm shift in transfer learning.
- 2023-05arXiv 2305.12827Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
Guillermo Ortiz-Jimenez, Alessandro Favero, Pascal Frossard · Advances in Neural Information Processing Systems 36 (NeurIPS 2023) · Machine learning
Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks, while negating them leads to task forgetting.
- 2023-05arXiv 2305.13281LM vs LM: Detecting Factual Errors via Cross Examination
Roi Cohen, May Hamri, Mor Geva et al. · Language models & NLP
A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically.
- 2023-05arXiv 2305.13300Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
Jian Xie, Kai Zhang, Jiangjie Chen et al. · Language models & NLP
By providing external information to large language models (LLMs), tool augmentation (including retrieval augmentation) has emerged as a promising solution for addressing the limitations of LLMs' static parametric memory.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsSuccessors should earn authority, not win contests: graded succession in continual learningStudy: Decision signatures for conflict detectionStudy: Graded succession by earned authorityStudy: Logical coherence of LLM world modelsStudy: Memory world models and source trustStudy: Model self knowledge and confident errors - 2023-05arXiv 2305.12295Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
Liangming Pan, Alon Albalak, Xinyi Wang et al. · Language models & NLP
Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which integrates LLMs with symbolic solvers to improve logical problem-solving.
- 2023-05arXiv 2305.09656SatLM: Satisfiability-Aided Language Models Using Declarative Prompting
Xi Ye, Qiaochu Chen, Isil Dillig et al. · Language models & NLP
Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning.
- 2023-04arXiv 2304.13734The Internal State of an LLM Knows When It's Lying
Amos Azaria, Tom Mitchell · Language models & NLP
While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone.
- 2023-04arXiv 2304.11949Geometric Relational Embeddings: A Survey
Bo Xiong, Mojtaba Nayyeri, Ming Jin et al. · AI & agents
Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions.
- 2023-03arXiv 2303.17651Self-Refine: Iterative Refinement with Self-Feedback
Aman Madaan, Niket Tandon, Prakhar Gupta et al. · Language models & NLP
Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
- 2023-03arXiv 2303.14186TRAK: Attributing Model Behavior at Scale
Sung Min Park, Kristian Georgiev, Andrew Ilyas et al. · Machine learning
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy.
- 2023-03arXiv 2303.11366Reflexion: Language Agents with Verbal Reinforcement Learning
Noah Shinn, Federico Cassano, Edward Berman et al. · AI & agents
, games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning.
- 2023-03arXiv 2303.08896SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Potsawee Manakul, Adian Liusie, Mark J. F. Gales · Language models & NLP
Generative Large Language Models (LLMs) such as GPT-3 are capable of generating highly fluent responses to a wide variety of user prompts. However, LLMs are known to hallucinate facts and make non-factual statements which can undermine trust in their output.
- 2023-01arXiv 2301.13379Faithful Chain-of-Thought Reasoning
Qing Lyu, Shreya Havaldar, Adam Stein et al. · Language models & NLP
faithfulness). We propose Faithful CoT, a reasoning framework involving two stages: Translation (Natural Language query symbolic reasoning chain) and Problem Solving (reasoning chain answer), using an LM and a deterministic solver respectively.
- 2023-01arXiv 2301.13196Looped Transformers as Programmable Computers
Angeliki Giannou, Shashank Rajput, Jy-yong Sohn et al. · Machine learning
We present a framework for using transformer networks as universal computers by programming them with specific weights and placing them in a loop. Our input sequence acts as a punchcard, consisting of instructions and memory for data read/writes.
- 2022-12arXiv 2212.07677Transformers learn in-context by gradient descent
Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo et al. · Machine learning
At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to gradient-based meta-learning formulations.
- 2022-12arXiv 2212.08073Constitutional AI: Harmlessness from AI Feedback
Yuntao Bai, Saurav Kadavath, Sandipan Kundu et al. · Language models & NLP
As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs.
- 2022-12arXiv 2212.03827Discovering Latent Knowledge in Language Models Without Supervision
Collin Burns, Haotian Ye, Dan Klein et al. · Language models & NLP
Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors that human evaluators can't detect.
- 2022-11arXiv 2211.15661What learning algorithm is in-context learning? Investigations with linear models
Ekin Akyürek, Dale Schuurmans, Jacob Andreas et al. · Machine learning
Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples presented in the input without further parameter updates.
- 2022-11arXiv 2211.11875Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference
Eric Mitchell, Joseph J. Noh, Siyan Li et al. · Language models & NLP
While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs.'.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsTrust the premises, not the confidence: which belief to drop when an LLM contradicts itself, and why the solver is not the bottleneckStudy: Logical coherence of LLM world modelsStudy: Orchestrated specialists and bridge synthesis - 2022-10arXiv 2210.13382Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Kenneth Li, Aspen K. Hopkins, David Bau et al. · Machine learning
Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see?
- 2022-10arXiv 2210.12217Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning
Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark · AI & agents
Our goal is a question-answering (QA) system that can show how its answers are implied by its own internal beliefs via a systematic chain of reasoning. Such a capability would allow better understanding of why a model produced the answer it did.
- 2022-10arXiv 2210.10760Scaling Laws for Reward Model Overoptimization
Leo Gao, John Schulman, Jacob Hilton · Machine learning
In reinforcement learning from human feedback, it is common to optimize against a reward model trained to predict human preferences. Because the reward model is an imperfect proxy, optimizing its value too much can hinder ground truth performance, in accordance with Goodhart's law.
Cited inReal judges did not break Best-of-N at N ≤ 32, and measured ε did not predict the budgetThurstone Bounds Best-of-N: A 1927 Identity, Calibrated for Modern VerifiersStudy: Generational competitive continual learningStudy: Genesys program prior artInternal notesStudy: Judge exploitability on real Best-of-NStudy: Logical coherence of LLM world modelsStudy: Stopping confident wrong expert votes - 2022-10arXiv 2210.05643A Kernel-Based View of Language Model Fine-Tuning
Sadhika Malladi, Alexander Wettig, Dingli Yu et al. · Machine learning
It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings., why fine-tuning a model with or more parameters on a couple dozen training points does not result in overfitting.
- 2022-05arXiv 2205.11822Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Jaehun Jung, Lianhui Qin, Sean Welleck et al. · Language models & NLP
Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this.
- 2022-05arXiv 2205.10128Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Zhaocheng Zhu, Mikhail Galkin, Zuobai Zhang et al. · AI & agents
Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning. Traditional symbolic methods traverse a complete knowledge graph to extract the answers, which provides good interpretation for each step.
- 2022-04arXiv 2204.14211TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
Joel Jang, Seonghyeon Ye, Changho Lee et al. · Language models & NLP
Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment.
- 2022-03arXiv 2203.14465STaR: Bootstrapping Reasoning With Reasoning
Eric Zelikman, Yuhuai Wu, Jesse Mu et al. · Machine learning
Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering.
- 2022-03arXiv 2203.11171Self-Consistency Improves Chain of Thought Reasoning in Language Models
Xuezhi Wang, Jason Wei, Dale Schuurmans et al. · Language models & NLP
Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting.
- 2021-11arXiv 2111.05498Attention Approximates Sparse Distributed Memory
Trenton Bricken, Cengiz Pehlevan · 35th Conference on Neural Information Processing Systems (NeurIPS 2021) · Machine learning
While Attention has come to be an important mechanism in deep learning, there remains limited intuition for why it works so well.
- 2021-10arXiv 2110.13715ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
Zhanqiu Zhang, Jie Wang, Jiajun Chen et al. · AI & agents
Query embedding (QE) -- which aims to embed entities and first-order logical (FOL) queries in low-dimensional spaces -- has shown great power in multi-hop reasoning over knowledge graphs.
- 2021-09arXiv 2109.14723BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Nora Kassner, Oyvind Tafjord, Hinrich Schütze et al. · Language models & NLP
Although pretrained language models (PTLMs) contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after specialized training.
- 2021-06arXiv 2106.14342Stabilizing Equilibrium Models by Jacobian Regularization
Shaojie Bai, Vladlen Koltun, J. Zico Kolter · Machine learning
Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer. These models have been shown to achieve performance competitive with the state-of-the-art deep networks while using significantly less memory.
- 2021-02arXiv 2102.01017Measuring and Improving Consistency in Pretrained Language Models
Yanai Elazar, Nora Kassner, Shauli Ravfogel et al. · Language models & NLP
Consistency of a model -- that is, the invariance of its behavior under meaning-preserving alternations in its input -- is a highly desirable property in natural language processing.
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.
