| Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus added by Syntology |
2026-08 (from id) |
StartLuxLabs/Massive-Activations-HLA/src/massive_activations_hla/capture/model_loading.py 4b04b5f6e4343de9 |
ran
|
MIT (permissive) |
| Beyond Scale and Generation: Understanding Language Model-based Entity Matching added by Syntology |
2026-07 (from id) |
Jantory/llm-trained-matcher/run_cross_dataset.py b539874a305789f6 |
unverified |
no licence file found · pointer only |
| Total Variation Distance Estimation in Autoregressive Models added by Syntology |
2026-07 (from id) |
XunZhiyang/llm-tv-estimation/experiments/tv_estimate.py 6348c83ab01fb9bd |
unverified |
MIT (permissive) |
| Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning added by Syntology |
2026-06 (from id) |
Richard-zrx/ADS/src/model_utils.py a079eb7fd6d1a19a |
ran
|
Apache-2.0 (permissive) |
| Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models added by Syntology |
2026-06 (from id) |
llaraspata/HallucinationDetection/src/model/utils.py 6f394e98c42552fb |
unverified |
no licence file found · pointer only |
| SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search added by Syntology |
2026-05 (from id) |
XMUDeepLIT/SAAS/search/generate_with_search.py 39d6a0aa1eaffc16 |
unverified |
Apache-2.0 (permissive) |
| PRISM: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning added by Syntology |
2026-05 (from id) |
LAMDA-CL/Prism/backbone/shared/model_loading.py 0f0205bc9e1110e2 |
unverified |
MIT (permissive) |
| Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders added by Syntology |
2026-05 (from id) |
shunchang-liu/pisa/src/detect_instability.py 0463d37512d2fda5 |
unverified |
no licence file found · pointer only |
| Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders added by Syntology |
2026-05 (from id) |
shunchang-liu/pisa/src/evaluate_rb2.py 472b67e46caa5c7d |
unverified |
no licence file found · pointer only |
| Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders added by Syntology |
2026-05 (from id) |
shunchang-liu/pisa/src/raw_feature_steering.py b155936dd212497a |
unverified |
no licence file found · pointer only |
| LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification added by Syntology |
2026-05 (from id) |
TioeAre/LaTER/later/src/analysis/plot_entropy_reasoning_curves.py 0e0355e6f4139423 |
unverified |
Apache-2.0 (permissive) |
| One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation added by Syntology |
2026-04 (from id) |
ejbito/InvariRank/invarirank/modeling.py 6d2f32351f12ba2b |
unverified |
MIT (permissive) |
| Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking added by Syntology |
2026-02 (from id) |
Iskar-Deng/DAM-learning/evaluation/eval_minpairs_acc.py 4bb1111352e82926 |
unverified |
no licence file found · pointer only |
| Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity added by Syntology |
2026-02 (from id) |
AI21Labs/in-context-ralm/ralm/model_utils.py cdd42d9143f7e2cd |
unverified |
Apache-2.0 (permissive) |
| TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs added by Syntology |
2026-01 (from id) |
furiosa-ai/TABED/tabed/modules/load_pretrained.py 433fce01b1f7cb60 |
unverified |
MIT (permissive) |
| Linear Dynamics in the RLVR Training of Large Language Models added by Syntology |
2026-01 (from id) |
Miaow-Lab/RLVR-Linearity/analysis/token_logprob/plot_token_logprob_linearity.py 974078a91d3ec703 |
unverified |
MIT (permissive) |
| Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers |
26 May 2025 |
mangopy/searchlm/src/_entropy.py a3518bfc816435e7 |
unverified |
Apache-2.0 (permissive) |
| OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation |
6 May 2025 |
OpenHelix-robot/OpenHelix/data_preprocessing/preprocess_calvin_instructions.py 1441fd48c61694c2 |
unverified |
MIT (permissive) |
| CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners |
20 Mar 2025 |
zjunlp/CaKE/Analysis/utils.py 91a41852736ee2f5 |
unverified |
MIT (permissive) |
| Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering |
15 Aug 2024 |
Oxford-AI-for-Society/human-learning-strategies/training/fine_tuning/shared_utils.py 12071bb621f4cba1 |
unverified |
GPL-3.0 (copyleft) · pointer only |
| Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon |
25 Jun 2024 |
eleutherai/semantic-memorization/inference.py a1952e4763d93dba |
unverified |
no licence file found · pointer only |
| Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries |
18 Jun 2024 |
edenbiran/HoppingTooLate/src/utils.py 8164e26307c3a60b |
ran
|
MIT (permissive) |
| Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport |
18 Jun 2024 |
brightjade/Opt-Out/model.py 3e34efa256660441 |
unverified |
MIT (permissive) |
| Stress-Testing Capability Elicitation With Password-Locked Models |
29 May 2024 |
FabienRoger/sandbagging/sandbagging/basic_model_info.py 009a49e66bf505da |
ran
|
no licence file found · pointer only |
| Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models |
27 May 2024 |
ShengYun-Peng/llm-landscape/src/llm/inference.py 0308de63e8fa3250 |
unverified |
MIT (permissive) |
| AutoPSV: Automated Process-Supervised Verifier |
27 May 2024 |
rookie-joe/autocv/data_annotation.py 17243183193565ff |
ran
|
no licence file found · pointer only |
| Keep It Private: Unsupervised Privatization of Online Text |
16 May 2024 |
csbao/kip-privatization/src/generate.py 5c7e9c77b1969bc7 |
unverified |
no licence file found · pointer only |
| The Platonic Representation Hypothesis |
13 May 2024 |
minyoungg/platonic-rep/models.py c420a7cf0eb5ab96 |
unverified |
no licence file found · pointer only |
| Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents |
24 Apr 2024 |
kortukov/realistic_knowledge_conflicts/src/model_utils.py 676e6dd24fe7e3b5 |
unverified |
no licence file found · pointer only |
| Towards Better Statistical Understanding of Watermarking LLMs |
19 Mar 2024 |
zhongzecai/dualga/WatermarkAlgorithm/utils/evaluation.py ff61ef7b3942bc85 |
unverified |
no licence file found · pointer only |
| SynCode: LLM Generation with Grammar Augmentation |
3 Mar 2024 |
uiuc-focal-lab/syncode/syncode/common.py ba0949d27e98d12e |
unverified |
MIT (permissive) |
| Greed is All You Need: An Evaluation of Tokenizer Inference Methods |
2 Mar 2024 |
melelbgu/tokenizers_intrinsic_benchmark/utils.py 07940de2cf1e2aa0 |
ran
|
MIT (permissive) |
| Dialect prejudice predicts AI decisions about people's character, employability, and criminality |
1 Mar 2024 |
valentinhofmann/dialect-prejudice/probing/helpers.py 8300552b36c2b281 |
unverified |
MIT (permissive) |
| RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records |
25 Feb 2024 |
ritaranx/RAM-EHR/model_src/utils.py dd27c40f658addad |
ran
|
MIT (permissive) |
| DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers |
25 Feb 2024 |
xirui-li/drattack/attack_prompt_data/uncensored_vicuna/uncensor.py f293af98d59df4d0 |
ran
|
MIT (permissive) |
| Defending LLMs against Jailbreaking Attacks via Backtranslation |
26 Feb 2024 |
yihanwang617/llm-jailbreaking-defense/llm_jailbreaking_defense/models.py ee5d16865ecd5e2b |
ran
|
MIT (permissive) |
| Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models |
24 Feb 2024 |
yihongdong/cdd-ted4llms/TED.py a1010269bb1357b3 |
unverified |
MIT (permissive) |
| Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models |
23 Feb 2024 |
jimxionggm/interactive-kbqa/predict/dialog_predictor.py e9916eef46c98f37 |
unverified |
no licence file found · pointer only |
| Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs |
19 Feb 2024 |
nicolas-bzrd/llm-recipes/models/models_utils.py 15baf103a0b4554f |
ran
|
no licence file found · pointer only |
| GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving |
15 Feb 2024 |
geoeval/geoeval/tool/tokenized_data.py 1c70706ba104f6dc |
ran
|
no licence file found · pointer only |
| Understanding the Weakness of Large Language Model Agents within a Complex Android Environment |
9 Feb 2024 |
androidarenaagent/androidarena/agents/utils.py 9ee661fad645d0f0 |
unverified |
no licence file found · pointer only |
| Evading Data Contamination Detection for Language Models is (too) Easy |
5 Feb 2024 |
eth-sri/malicious-contamination/src/contamination/basic_model_loader.py c29c23246ee520ad |
unverified |
Apache-2.0 (permissive) |
| On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning |
21 Dec 2023 |
cambridgeltl/ensembled-sicl/utils/load_model.py 618ad395c8046ae0 |
unverified |
no licence file found · pointer only |
| Controlled Text Generation via Language Model Arithmetic |
24 Nov 2023 |
eth-sri/language-model-arithmetic/src/model_arithmetic/basic_model_loader.py c29c23246ee520ad |
unverified |
MIT (permissive) |
| Tree Prompting: Efficient Task Adaptation without Fine-Tuning |
21 Oct 2023 |
csinva/tree-prompt/treeprompt/llm_utils.py cfcb2eef36f5b7ab |
unverified |
no licence file found · pointer only |
| Language Models Represent Space and Time |
3 Oct 2023 |
wesg52/world-models/make_prompt_datasets.py ec78e0b3d6261ed5 |
unverified |
MIT (permissive) |
| ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers |
28 Sep 2023 |
kuleshov-group/llmtools/llmtools/executor.py a2178676d3e7abdd |
ran
|
no licence file found · pointer only |
| The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" |
21 Sep 2023 |
lukasberglund/reversal_curse/src/models/common.py e18553bc097d701c |
unverified |
no licence file found · pointer only |
| Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias |
28 Jun 2023 |
yueyu1030/attrprompt/train_classifier/plm_model/utils.py dd27c40f658addad |
ran
|
Apache-2.0 (permissive) |
| Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection |
22 May 2023 |
Uppaal/lm-ood/utils/model_utils.py bb9cc88f0bea27c4 |
unverified |
MIT (permissive) |
| Prompting with Pseudo-Code Instructions |
19 May 2023 |
mayank31398/pseudo-code-instructions/code_instruct/model.py 35ab7eb005ae0a76 |
unverified |
Apache-2.0 (permissive) |
| TinyStories: How Small Can Language Models Be and Still Speak Coherent English? |
12 May 2023 |
danbraunai/simple_stories_train/simple_stories_train/tokenizer.py c430eca0b62e5574 |
unverified |
MIT (permissive) |
| Neighborhood-Regularized Self-Training for Learning with Few Labels |
10 Jan 2023 |
ritaranx/NeST/utils.py 661491a0aadeb24e |
unverified |
MIT (permissive) |
| Parallel Context Windows for Large Language Models |
21 Dec 2022 |
AI21Labs/Parallel-Context-Windows/model_loaders.py cbb2c50ff3858a3f |
unverified |
Apache-2.0 (permissive) |
| Instruction-driven history-aware policies for robotic manipulations |
11 Sep 2022 |
guhur/hiveformer/preprocess_instructions.py 1441fd48c61694c2 |
unverified |
MIT (permissive) |
| LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale |
15 Aug 2022 |
huggingface/transformers-bloom-inference/inference_server/models/model.py 835634e64b6b277d |
unverified |
Apache-2.0 (permissive) |
| RoBERTuito: a pre-trained language model for social media text in Spanish |
18 Nov 2021 |
pysentimiento/robertuito/finetune_vs_scratch/model.py 6898279b83309763 |
unverified |
MIT (permissive) |
| Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems |
1 Apr 2021 |
asappresearch/abcd/utils/load.py 10442a3755e649e8 |
unverified |
MIT (permissive) |
| Swin Transformer: Hierarchical Vision Transformer using Shifted Windows |
25 Mar 2021 |
YongWookHa/swin-transformer-ocr/utils.py f299bd819038020a |
unverified |
MIT (permissive) |
| Emergent Multi-Agent Communication in the Deep Learning Era |
3 Jun 2020 |
brendon-boldt/xferbench/xferbench/model/mt.py 10a49786ffff4dd4 |
unverified |
MIT (permissive) |
| word2word: A Collection of Bilingual Lexicons for 3,564 Language Pairs |
27 Nov 2019 |
Kyubyong/word2word/word2word/tokenization.py 349ed3bbc388de65 |
unverified |
Apache-2.0 (permissive) |
| Enriching Pre-trained Language Model with Entity Information for Relation Classification |
20 May 2019 |
chielingyueh/anaphora_resolution_chemical_patents/utils.py 057777fc1e9365c2 |
unverified |
Apache-2.0 (permissive) |
| MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization |
12 Oct 2018 |
megagonlabs/coop/coop/util.py bcb4a8a6eebef981 |
unverified |
BSD-3-Clause (permissive) |
| arXiv:openreview_g9G7qyAzki |
|
The-Inscrutable-X/CalibratedModelAgnosticCorrectness/utils/model_utils.py 65b86daaedb4ee28 |
unverified |
Apache-2.0 (permissive) |
| arXiv:aaai_29784 |
|
HITsz-TMG/Ext-Sub/eval/ngram_rep_eval.py e65a8e07bf87b809 |
unverified |
MIT (permissive) |
| arXiv:2023.findings-ijcnlp.4 |
|
brightjade/PRiSM/models/utils.py 59ee54f46b531e61 |
unverified |
MIT (permissive) |
| arXiv:2023.acl-long.119 |
|
lsvih/AtTGen/tokenizer.py 7e6ffd70f8da3b41 |
unverified |
MIT (permissive) |
| arXiv:2021.findings-acl.173 |
|
sysulic/MDGI/models/util.py 70b1c0f23ec51e7a |
unverified |
MIT (permissive) |