https://borgr.github.io/ https://borgr.github.io/papers/ https://borgr.github.io/guides/ https://borgr.github.io/papers/ties-merging-resolving-interference-when-merging-models/ https://borgr.github.io/papers/tinybenchmarks-evaluating-llms-with-fewer-examples/ https://borgr.github.io/papers/active-learning-for-bert-an-empirical-study/ https://borgr.github.io/papers/findings-of-the-babylm-challenge-sample-efficient-pretrainin/ https://borgr.github.io/papers/global-mmlu-understanding-and-addressing-cultural-and-lingui/ https://borgr.github.io/papers/an-autonomous-debating-system/ https://borgr.github.io/papers/q2-evaluating-factual-consistency-in-knowledge-grounded-dial/ https://borgr.github.io/papers/on-the-weaknesses-of-reinforcement-learning-for-neural-machi/ https://borgr.github.io/papers/fusing-finetuned-models-for-better-pretraining/ https://borgr.github.io/papers/disentqa-disentangling-parametric-and-contextual-knowledge-w/ https://borgr.github.io/papers/model-merging-with-svd-to-tie-the-knots/ https://borgr.github.io/papers/beyond-binary-rewards-training-lms-to-reason-about-their-unc/ https://borgr.github.io/papers/jump-to-conclusions-short-cutting-transformers-with-linear-t/ https://borgr.github.io/papers/asymmetry-in-low-rank-adapters-of-foundation-models/ https://borgr.github.io/papers/efficient-multi-prompt-evaluation-of-llms/ https://borgr.github.io/papers/call-for-papers-the-babylm-challenge-sample-efficient-pretra/ https://borgr.github.io/papers/are-you-convinced-choosing-the-more-convincing-evidence-with/ https://borgr.github.io/papers/knowledge-is-a-region-in-weight-space-for-fine-tuned-languag/ https://borgr.github.io/papers/will-it-blend-blending-weak-and-strong-labeled-data-in-a-neu/ https://borgr.github.io/papers/corpus-wide-argument-mining-a-working-solution/ https://borgr.github.io/papers/dora-the-explorer-directed-outreaching-reinforcement-action/ https://borgr.github.io/papers/efficient-benchmarking-of-language-models/ https://borgr.github.io/papers/elements-of-world-knowledge-ewok-a-cognition-inspired-framew/ https://borgr.github.io/papers/a-survey-on-model-moerging-recycling-and-routing-among-speci/ https://borgr.github.io/papers/findings-of-the-second-babylm-challenge-sample-efficient-pre/ https://borgr.github.io/papers/cold-fusion-collaborative-descent-for-distributed-multitask/ https://borgr.github.io/papers/let-s-agree-to-agree-neural-networks-share-classification-or/ https://borgr.github.io/papers/numerologic-number-encoding-for-enhanced-llms-numerical-reas/ https://borgr.github.io/papers/the-grammar-learning-trajectories-of-neural-language-models/ https://borgr.github.io/papers/call-for-papers-the-2nd-babylm-challenge-sample-efficient-pr/ https://borgr.github.io/papers/semeval-2019-task-1-cross-lingual-semantic-parsing-with-ucca/ https://borgr.github.io/papers/inherent-biases-in-reference-based-evaluation-for-grammatica/ https://borgr.github.io/papers/genie-achieving-human-parity-in-content-grounded-datasets-ge/ https://borgr.github.io/papers/reference-less-measure-of-faithfulness-for-grammatical-error/ https://borgr.github.io/papers/automatic-metric-validation-for-grammatical-error-correction/ https://borgr.github.io/papers/babylm-turns-3-call-for-papers-for-the-2025-babylm-workshop/ https://borgr.github.io/papers/bigger-is-not-always-better-the-importance-of-human-scale-la/ https://borgr.github.io/papers/learning-to-combine-grammatical-error-corrections/ https://borgr.github.io/papers/where-to-start-analyzing-the-potential-value-of-intermediate/ https://borgr.github.io/papers/compress-then-serve-serving-thousands-of-lora-adapters-with/ https://borgr.github.io/papers/deductive-closure-training-of-language-models-for-coherence/ https://borgr.github.io/papers/cluster-tune-boost-cold-start-performance-in-text-classifica/ https://borgr.github.io/papers/sloth-scaling-laws-for-llm-skills-to-predict-multi-benchmark/ https://borgr.github.io/papers/the-language-of-legal-and-illegal-activity-on-the-darknet/ https://borgr.github.io/papers/zipnn-lossless-compression-for-ai-models/ https://borgr.github.io/papers/unitxt-flexible-shareable-and-reusable-data-preparation-and/ https://borgr.github.io/papers/data-contamination-report-from-the-2024-conda-shared-task/ https://borgr.github.io/papers/classifying-syntactic-errors-in-learner-language/ https://borgr.github.io/papers/when-ai-benchmarks-plateau-a-systematic-study-of-benchmark-s/ https://borgr.github.io/papers/a-hitchhiker-s-guide-to-scaling-law-estimation/ https://borgr.github.io/papers/benchmark-agreement-testing-done-right-a-guide-for-llm-bench/ https://borgr.github.io/papers/dove-a-large-scale-multi-dimensional-predictions-dataset-tow/ https://borgr.github.io/papers/compeft-compression-for-communicating-parameter-efficient-up/ https://borgr.github.io/papers/label-sleuth-from-unlabeled-text-to-a-classifier-in-a-few-ho/ https://borgr.github.io/papers/automatically-extracting-challenge-sets-for-non-local-phenom/ https://borgr.github.io/papers/livexiv-a-multi-modal-live-benchmark-based-on-arxiv-papers-c/ https://borgr.github.io/papers/beneath-the-surface-of-consistency-exploring-cross-lingual-k/ https://borgr.github.io/papers/findings-of-the-third-babylm-challenge-accelerating-language/ https://borgr.github.io/papers/the-future-of-open-human-feedback/ https://borgr.github.io/papers/label-efficient-model-selection-for-text-generation/ https://borgr.github.io/papers/fuse-to-forget-bias-reduction-and-selective-memorization-thr/ https://borgr.github.io/papers/human-learning-by-model-feedback-the-dynamics-of-iterative-p/ https://borgr.github.io/papers/mediators-in-determining-what-processing-bert-performs-first/ https://borgr.github.io/papers/lossless-and-near-lossless-compression-for-foundation-models/ https://borgr.github.io/papers/unsupervised-expressive-rules-provide-explainability-and-ass/ https://borgr.github.io/papers/naturally-occurring-feedback-is-common-extractable-and-usefu/ https://borgr.github.io/papers/the-mighty-torr-a-benchmark-for-table-reasoning-and-robustne/ https://borgr.github.io/papers/semantics-aware-attention-improves-neural-machine-translatio/ https://borgr.github.io/papers/prequel-quality-estimation-of-machine-translation-outputs-in/ https://borgr.github.io/papers/serrant-a-syntactic-classifier-for-english-grammatical-error/ https://borgr.github.io/papers/the-sharelm-collection-and-plugin-contributing-human-model-c/ https://borgr.github.io/papers/global-piqa-evaluating-commonsense-reasoning-across-100-lang/ https://borgr.github.io/papers/general-agent-evaluation/ https://borgr.github.io/papers/neurips-2023-llm-efficiency-fine-tuning-competition/ https://borgr.github.io/papers/navigating-the-modern-evaluation-landscape-considerations-in/ https://borgr.github.io/papers/enhancing-the-transformer-decoder-with-transition-based-synt/ https://borgr.github.io/papers/grasp-a-library-for-extracting-and-exploring-human-interpret/ https://borgr.github.io/papers/reinforcement-learning-with-large-action-spaces-for-neural-m/ https://borgr.github.io/papers/commonlid-re-evaluating-state-of-the-art-language-identifica/ https://borgr.github.io/papers/textarena/ https://borgr.github.io/papers/holmes-a-benchmark-to-assess-the-linguistic-competence-of-la/ https://borgr.github.io/papers/comsum-commit-messages-summarization-and-meaning-preservatio/ https://borgr.github.io/papers/do-llms-benefit-from-their-own-words/ https://borgr.github.io/papers/errormap-and-erroratlas-charting-the-failure-landscape-of-la/ https://borgr.github.io/papers/babybabellm-a-multilingual-benchmark-of-developmentally-plau/ https://borgr.github.io/papers/pretraining-language-models-for-diachronic-linguistic-change/ https://borgr.github.io/papers/unforgettable-generalization-in-language-models/ https://borgr.github.io/papers/cube-a-standard-for-unifying-agent-benchmarks/ https://borgr.github.io/papers/mediocrity-is-the-key-for-llm-as-a-judge-anchor-selection/ https://borgr.github.io/papers/mindgames-a-live-arena-for-evaluating-social-and-strategic-r/ https://borgr.github.io/papers/robustness-as-an-emergent-property-of-task-performance/ https://borgr.github.io/papers/will-it-merge-on-the-causes-of-model-mergeability/ https://borgr.github.io/papers/llm-hypnosis-exploiting-user-feedback-for-unauthorized-knowl/ https://borgr.github.io/papers/on-neurons-invariant-to-sentence-structural-changes-in-neura/ https://borgr.github.io/papers/semeval-2019-shared-task-cross-lingual-semantic-parsing-with/ https://borgr.github.io/papers/every-eval-ever-a-unifying-schema-and-community-repository-f/ https://borgr.github.io/papers/babylm-turns-4-and-goes-multilingual-call-for-papers-for-the/ https://borgr.github.io/papers/automated-discovery-has-no-universally-superior-harness/ https://borgr.github.io/papers/how-safe-is-your-safety-metric-automatic-concatenation-tests/ https://borgr.github.io/papers/a-latent-variable-framework-for-scaling-laws-in-large-langua/ https://borgr.github.io/papers/part-of-speech-and-universal-dependency-effects-on-english-a/ https://borgr.github.io/papers/resolving-interference-ri-disentangling-models-for-improved/ https://borgr.github.io/papers/instructions-shape-production-of-language-not-processing/ https://borgr.github.io/papers/growing-pains-extensible-and-efficient-llm-benchmarking-via/ https://borgr.github.io/papers/evaluation-cards-an-interpretive-layer-for-ai-evaluation-rep/ https://borgr.github.io/papers/position-agentic-systems-should-be-general/ https://borgr.github.io/papers/stop-guessing-when-to-stop-testing-efficient-model-evaluatio/ https://borgr.github.io/papers/cross-lingual-exploration-for-parametric-knowledge/ https://borgr.github.io/papers/crisp-complex-reasoning-with-interpretable-step-based-plans/ https://borgr.github.io/papers/can-gradient-descent-simulate-prompting/ https://borgr.github.io/papers/a-statistical-framework-for-game-based-ai-evaluation/ https://borgr.github.io/papers/muler-detailed-and-scalable-reference-based-evaluation/ https://borgr.github.io/papers/some-grammatical-errors-are-frequent-others-are-important/