| | Incremental Construction of Minimal Acyclic Finite-State Automata (2000) [pdf] (aclanthology.org) |
| 4 points by todsacerdoti 5 days ago | past | discuss |
|
| | Decompiling Binary Code with Large Language Models [pdf] (aclanthology.org) |
| 1 point by blenderob 6 days ago | past | discuss |
|
| | AI Moderation: Inconsistencies in Hate Speech Detection Across LLM-Based Systems (aclanthology.org) |
| 3 points by giuliomagnifico 42 days ago | past |
|
| | Native Sparse Attention (aclanthology.org) |
| 139 points by CalmStorm 83 days ago | past | 31 comments |
|
| | Evaluating the factuality of verifiable claims in long-form text generation (aclanthology.org) |
| 9 points by gone35 3 months ago | past | 1 comment |
|
| | Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing, Improving LLMs [pdf] (aclanthology.org) |
| 3 points by indigodaddy 6 months ago | past |
|
| | Large Language Models in Machine Translation (2007) [pdf] (aclanthology.org) |
| 1 point by Anon84 6 months ago | past |
|
| | Can AI Make Us Laugh? Comparing Jokes Generated by AI and a Human Expert [pdf] (aclanthology.org) |
| 2 points by Jimmc414 8 months ago | past |
|
| | HumanRankEval: Automatically Evaluating Conversational AI Output (aclanthology.org) |
| 2 points by MutedEstate45 9 months ago | past |
|
| | LLMs Help Humans Verify Truthfulness – Except When They Are Convincingly Wrong (aclanthology.org) |
| 2 points by rntn 9 months ago | past |
|
| | Dosa: Dataset of Social Artifacts from Different Indian Geographical Subcultures [pdf] (aclanthology.org) |
| 1 point by gnabgib 9 months ago | past |
|
| | A Confederacy of Models: A Comprehensive Evaluation of LLMs on Creative Writing (aclanthology.org) |
| 4 points by handfuloflight 10 months ago | past |
|
| | Graph Language Models (aclanthology.org) |
| 123 points by Anon84 on Sept 3, 2024 | past | 14 comments |
|
| | Dr ChatGPT: How different prompts impact health answer correctness (aclanthology.org) |
| 1 point by belter on April 10, 2024 | past |
|
| | Most Language Models can be Poets too (2022) [pdf] (aclanthology.org) |
| 1 point by tosh on Feb 3, 2024 | past |
|
| | Finite-State Transducers in Language and Speech Processing (1997) (aclanthology.org) |
| 3 points by yeesian on Nov 1, 2023 | past | 1 comment |
|
| | The Unreasonable Effectiveness of Transformer in Grammatical Error Correction (aclanthology.org) |
| 1 point by teleforce on Sept 17, 2023 | past | 1 comment |
|
| | What the DAAM: Interpreting Stable Diffusion Using Cross Attention (aclanthology.org) |
| 2 points by rayshan on Sept 11, 2023 | past |
|
| | Large language models with controllable working memory (aclanthology.org) |
| 5 points by xinwangmath on Sept 8, 2023 | past |
|
| | Text Classification with Gzip vs. Neural Networks [pdf] (aclanthology.org) |
| 3 points by haxiomic on Aug 16, 2023 | past |
|
| | Tracking the Trails of Political Biases Leading to Unfair NLP Models [pdf] (aclanthology.org) |
| 2 points by RafelMri on Aug 13, 2023 | past | 1 comment |
|
| | A Parameter-Free Classification Method with Compressors [pdf] (aclanthology.org) |
| 3 points by PikelEmi on July 29, 2023 | past |
|
| | Text classification using gzip competitive with Transformers [pdf] (aclanthology.org) |
| 3 points by atrudeau on July 13, 2023 | past |
|
| | A Parameter-Free Classification Method with Compressors (aclanthology.org) |
| 83 points by danielam on July 13, 2023 | past | 8 comments |
|
| | A 2007 paper from Jeff Dean on a 2T token 300B parameter LLM [pdf] (aclanthology.org) |
| 1 point by abhi9u on June 1, 2023 | past |
|
| | Bert and XLNet: 85% Neurons Redundant, 92% Removable for Downstream Tasks [pdf] (aclanthology.org) |
| 3 points by leumassuehtam on April 15, 2023 | past |
|
| | LittleBird: Efficient Faster and Longer Transformer for Question Answering [pdf] (aclanthology.org) |
| 2 points by PaulHoule on April 14, 2023 | past |
|
| | What Will It Take to Fix Benchmarking in Natural Language Understanding? (2021) (aclanthology.org) |
| 1 point by YeGoblynQueenne on March 14, 2023 | past |
|
| | The Covid That Wasn’t: Counterfactual Journalism Using GPT (aclanthology.org) |
| 2 points by dakial1 on March 6, 2023 | past | 1 comment |
|
| | Emergent Structures and Training Dynamics in Large Language Models (aclanthology.org) |
| 2 points by CrypticShift on Feb 5, 2023 | past |
|
|
| More |
