{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"1906.00591","title":"Evaluating Gender Bias in Machine Translation","created":"2019-06-03","cited_by_count":249},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225},{"id":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"2305.07375","title":"Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation","created":"2023-05-12","cited_by_count":69},{"id":"2312.03813","title":"Improving Activation Steering in Language Models with Mean-Centring","created":"2023-12-06","cited_by_count":68},{"id":"2308.10835","title":"Enhancing Recommender Systems with Large Language Model Reasoning Graphs","created":"2023-08-21","cited_by_count":52},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51},{"id":"2106.02881","title":"Graph Infomax Adversarial Learning for Treatment Effect Estimation with Networked Observational Data","created":"2021-06-05","cited_by_count":42},{"id":"2308.10837","title":"Leveraging Large Language Models for Pre-trained Recommender Systems","created":"2023-08-21","cited_by_count":42},{"id":"2203.12258","title":"Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View","created":"2022-03-23","cited_by_count":31},{"id":"2009.06828","title":"Matching in Selective and Balanced Representation Space for Treatment Effects Estimation","created":"2020-09-15","cited_by_count":30},{"id":"2105.14553","title":"Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice","created":"2021-05-30","cited_by_count":30},{"id":"2312.06677","title":"Intelligent Virtual Assistants with LLM-based Process Automation","created":"2023-12-04","cited_by_count":26},{"id":"2301.09211","title":"An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models","created":"2023-01-22","cited_by_count":24},{"id":"2310.04993","title":"Prompt-augmented Temporal Point Process for Streaming Event Sequence","created":"2023-10-08","cited_by_count":24},{"id":"2401.08217","title":"LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation","created":"2024-01-16","cited_by_count":19},{"id":"2202.00436","title":"ROCK: Causal Inference Principles for Reasoning about Commonsense Causality","created":"2022-01-31","cited_by_count":16},{"id":"2112.05194","title":"Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving","created":"2021-12-09","cited_by_count":11},{"id":"2202.10885","title":"Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data","created":"2022-02-22","cited_by_count":9},{"id":"2312.16113","title":"Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction","created":"2023-12-20","cited_by_count":9},{"id":"2402.03628","title":"Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies","created":"2024-02-06","cited_by_count":9},{"id":"2310.17784","title":"Data-Centric Financial Large Language Models","created":"2023-10-07","cited_by_count":8},{"id":"2401.11335","title":"Deception and Manipulation in Generative AI","created":"2024-01-20","cited_by_count":8},{"id":"2305.17727","title":"Learning a Structural Causal Model for Intuition Reasoning in Conversation","created":"2023-05-28","cited_by_count":7},{"id":"2203.05123","title":"Multi-Task Adversarial Learning for Treatment Effect Estimation in Basket Trials","created":"2022-03-10","cited_by_count":6},{"id":"2207.01911","title":"Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications","created":"2022-07-05","cited_by_count":6},{"id":"2209.09482","title":"Incorporating Causal Analysis into Diversified and Logical Response Generation","created":"2022-09-20","cited_by_count":4}],"next_cursor":null}