{"list":"other","total":80,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195},{"id":"2311.05553","title":"Removing RLHF Protections in GPT-4 via Fine-Tuning","created":"2023-11-09","cited_by_count":171},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"1909.06321","title":"End-to-End Bias Mitigation by Modelling Biases in Corpora","created":"2019-09-13","cited_by_count":128},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111},{"id":"2206.15475","title":"Causal Machine Learning: A Survey and Open Problems","created":"2022-06-30","cited_by_count":110},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91},{"id":"2402.05119","title":"A Closer Look at the Limitations of Instruction Tuning","created":"2024-02-03","cited_by_count":77},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76},{"id":"2407.17436","title":"AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies","created":"2024-07-11","cited_by_count":74},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70},{"id":"2109.05642","title":"On the Impact of Spurious Correlation for Out-of-distribution Detection","created":"2021-09-12","cited_by_count":68},{"id":"2305.09857","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","created":"2023-05-17","cited_by_count":68},{"id":"2012.10040","title":"Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals","created":"2020-12-18","cited_by_count":67},{"id":"2306.11270","title":"Evaluating the Zero-shot Robustness of Instruction-tuned Language Models","created":"2023-06-20","cited_by_count":66},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65},{"id":"2010.02458","title":"Identifying Spurious Correlations for Robust Text Classification","created":"2020-10-06","cited_by_count":59},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59},{"id":"1711.08792","title":"SPINE: SParse Interpretable Neural Embeddings","created":"2017-11-23","cited_by_count":55},{"id":"2305.11383","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","created":"2023-05-19","cited_by_count":49},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48},{"id":"2402.18243","title":"Learning or Self-aligning? Rethinking Instruction Fine-tuning","created":"2024-02-28","cited_by_count":43},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41},{"id":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24},{"id":"2306.14101","title":"Language models are weak learners","created":"2023-06-25","cited_by_count":22},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18},{"id":"2212.11237","title":"Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators","created":"2022-12-21","cited_by_count":17},{"id":"2408.05859","title":"The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms","created":"2024-08-11","cited_by_count":13},{"id":"2305.13654","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","created":"2023-05-23","cited_by_count":11},{"id":"2405.03649","title":"Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation","created":"2024-05-06","cited_by_count":10},{"id":"2310.02953","title":"JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning","created":"2023-10-04","cited_by_count":6},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4},{"id":"2406.01976","title":"Conditional Language Learning with Context","created":"2024-06-04","cited_by_count":4}],"next_cursor":null}