{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/get-embeddings","entry":"get_embeddings","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":56,"n_papers_ran":19,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":47,"n_samples_ran":14,"n_samples_fingerprinted":0,"n_places":58,"n_places_pointer_only":17,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":1,"ran":9,"unverified":33},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2603.03081","paper":"/paper/arxiv-2603-03081","title":"TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ZevineXu/TAO-Attack","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/ZevineXu/TAO-Attack/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f556dda0785f3c77","mcp_get_code":{"code_sha256":"f556dda0785f3c77"}},{"arxiv_id":"2602.04941","paper":"/paper/arxiv-2602-04941","title":"Improving Set Function Approximation with Quasi-Arithmetic Neural Networks","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"tomastokar/Quasi-Arithmetic-Neural-Networks","path":"MNIST_qualitative.py","file_url":"https://github.com/tomastokar/Quasi-Arithmetic-Neural-Networks/blob/HEAD/MNIST_qualitative.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d4aa88c9ae85da11","mcp_get_code":{"code_sha256":"d4aa88c9ae85da11"}},{"arxiv_id":"2601.17230","paper":"/paper/arxiv-2601-17230","title":"CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"idirlab/CaseFacts","path":"experiments/check_similarity.py","file_url":"https://github.com/idirlab/CaseFacts/blob/HEAD/experiments/check_similarity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a5a629d94ddef395","mcp_get_code":{"code_sha256":"a5a629d94ddef395"}},{"arxiv_id":"2601.12263","paper":"/paper/arxiv-2601-12263","title":"Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"glad-lab/MGEO","path":"attack_autodan.py","file_url":"https://github.com/glad-lab/MGEO/blob/HEAD/attack_autodan.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19c802b4dd21c8b8","mcp_get_code":{"code_sha256":"19c802b4dd21c8b8"}},{"arxiv_id":"2512.11437","paper":"/paper/arxiv-2512-11437","title":"CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"AikyamLab/clinic","path":"evaluation/adverserial/adv_eval.py","file_url":"https://github.com/AikyamLab/clinic/blob/HEAD/evaluation/adverserial/adv_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e51b60b9add827b6","mcp_get_code":{"code_sha256":"e51b60b9add827b6"}},{"arxiv_id":"2512.11437","paper":"/paper/arxiv-2512-11437","title":"CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"AikyamLab/clinic","path":"evaluation/consistency/consistency_eval.py","file_url":"https://github.com/AikyamLab/clinic/blob/HEAD/evaluation/consistency/consistency_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"daf8bacd15f6bdea","mcp_get_code":{"code_sha256":"daf8bacd15f6bdea"}},{"arxiv_id":"2509.15786","paper":"/paper/arxiv-2509-15786","title":"Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"aida-ugent/CLIMB","path":"src/get_embeddings.py","file_url":"https://github.com/aida-ugent/CLIMB/blob/HEAD/src/get_embeddings.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5eb54fb92e768705","mcp_get_code":{"code_sha256":"5eb54fb92e768705"}},{"arxiv_id":"2503.06202","paper":"/paper/breaking-free-from-mmi-a-new-frontier-in","title":"Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization","date":"2025-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jugechengzi/Rationalization-N2R","path":"embedding.py","file_url":"https://github.com/jugechengzi/Rationalization-N2R/blob/HEAD/embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7fd4428a7a26977","mcp_get_code":{"code_sha256":"a7fd4428a7a26977"}},{"arxiv_id":"2502.10436","paper":"/paper/merge-3-efficient-evolutionary-merging-on","title":"MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs","date":"2025-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tommasomncttn/merge3","path":"src/mergenetic/analysis/representation.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/analysis/representation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1286c013573044fc","mcp_get_code":{"code_sha256":"1286c013573044fc"}},{"arxiv_id":"2502.06485","paper":"/paper/wyckoffdiff-a-generative-diffusion-model-for","title":"WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry","date":"2025-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"httk/wyckoffdiff","path":"wyckoff_generation/evaluation/compute_fwd.py","file_url":"https://github.com/httk/wyckoffdiff/blob/HEAD/wyckoff_generation/evaluation/compute_fwd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"408fa913477a97c5","mcp_get_code":{"code_sha256":"408fa913477a97c5"}},{"arxiv_id":"2412.11716","paper":"/paper/llms-can-simulate-standardized-patients-via","title":"LLMs Can Simulate Standardized Patients via Agent Coevolution","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjumai/evopatient","path":"embedding_function/sentence_embedding.py","file_url":"https://github.com/zjumai/evopatient/blob/HEAD/embedding_function/sentence_embedding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc512197798fe2a7","mcp_get_code":{"code_sha256":"fc512197798fe2a7"}},{"arxiv_id":"2411.11706","paper":"/paper/mc-llava-multi-concept-personalized-vision","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arctanxarc/mc-llava","path":"train/train_joint.py","file_url":"https://github.com/arctanxarc/mc-llava/blob/HEAD/train/train_joint.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5db573c804b47ea8","mcp_get_code":{"code_sha256":"5db573c804b47ea8"}},{"arxiv_id":"2411.06646","paper":"/paper/understanding-scaling-laws-with-statistical","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dahoas/transformer_manifolds_learning","path":"embeddings.py","file_url":"https://github.com/dahoas/transformer_manifolds_learning/blob/HEAD/embeddings.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a4824be70cdf2b77","mcp_get_code":{"code_sha256":"a4824be70cdf2b77"}},{"arxiv_id":"2411.04420","paper":"/paper/bendvlm-test-time-debiasing-of-vision","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"waltergerych/bend_vlm","path":"bend_utils.py","file_url":"https://github.com/waltergerych/bend_vlm/blob/HEAD/bend_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"050b743339edef0b","mcp_get_code":{"code_sha256":"050b743339edef0b"}},{"arxiv_id":"2410.08113","paper":"/paper/robust-ai-generated-text-detection-by","title":"Robust AI-Generated Text Detection by Restricted Embeddings","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"silversolver/robustatd","path":"fit_eraser_probing_tasks.py","file_url":"https://github.com/silversolver/robustatd/blob/HEAD/fit_eraser_probing_tasks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e99730bed9668d68","mcp_get_code":{"code_sha256":"e99730bed9668d68"}},{"arxiv_id":"2410.06003","paper":"/paper/is-the-mmi-criterion-necessary-for","title":"Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jugechengzi/Rationalization-MRD","path":"embedding.py","file_url":"https://github.com/jugechengzi/Rationalization-MRD/blob/HEAD/embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7fd4428a7a26977","mcp_get_code":{"code_sha256":"a7fd4428a7a26977"}},{"arxiv_id":"2409.18073","paper":"/paper/infer-human-s-intentions-before-following","title":"Infer Human's Intentions Before Following Natural Language Instructions","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simon-wan/fiser","path":"networks/embeddings.py","file_url":"https://github.com/simon-wan/fiser/blob/HEAD/networks/embeddings.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"16b037202af1a18b","mcp_get_code":{"code_sha256":"16b037202af1a18b"}},{"arxiv_id":"2409.09811","paper":"/paper/prose-fd-a-multimodal-pde-foundation-model","title":"PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics","date":"2024-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"felix-lyx/prose","path":"prose_fd/models/attention_utils.py","file_url":"https://github.com/felix-lyx/prose/blob/HEAD/prose_fd/models/attention_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df45f4439f402a46","mcp_get_code":{"code_sha256":"df45f4439f402a46"}},{"arxiv_id":"2409.02772","paper":"/paper/unifying-causal-representation-learning-with","title":"Unifying Causal Representation Learning with the Invariance Principle","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"causallearningai/istant","path":"src/model.py","file_url":"https://github.com/causallearningai/istant/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2c6795c770350e2","mcp_get_code":{"code_sha256":"c2c6795c770350e2"}},{"arxiv_id":"2407.12784","paper":"/paper/agentpoison-red-teaming-llm-agents-via","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/AgentPoison","path":"algo/utils.py","file_url":"https://github.com/BillChan226/AgentPoison/blob/HEAD/algo/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"655e5409659cee36","mcp_get_code":{"code_sha256":"655e5409659cee36"}},{"arxiv_id":"2406.19130","paper":"/paper/evidential-concept-embedding-models-towards","title":"Evidential Concept Embedding Models: Towards Reliable Concept Explanations for Skin Disease Diagnosis","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"obiyoag/evi-cem","path":"learn_cavs.py","file_url":"https://github.com/obiyoag/evi-cem/blob/HEAD/learn_cavs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6cd52c2775a843cb","mcp_get_code":{"code_sha256":"6cd52c2775a843cb"}},{"arxiv_id":"2406.01288","paper":"/paper/improved-few-shot-jailbreaking-can-circumvent","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/I-FSJ","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/sail-sg/I-FSJ/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f556dda0785f3c77","mcp_get_code":{"code_sha256":"f556dda0785f3c77"}},{"arxiv_id":"2405.21018","paper":"/paper/improved-techniques-for-optimization-based","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaxiaojunqaq/i-gcg","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/jiaxiaojunqaq/i-gcg/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f556dda0785f3c77","mcp_get_code":{"code_sha256":"f556dda0785f3c77"}},{"arxiv_id":"2405.18780","paper":"/paper/quantitative-certification-of-bias-in-large","title":"Quantitative Certification of Bias in Large Language Models","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuc-focal-lab/LLMCert-B","path":"utils.py","file_url":"https://github.com/uiuc-focal-lab/LLMCert-B/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"e00307369c36acc3","mcp_get_code":{"code_sha256":"e00307369c36acc3"}},{"arxiv_id":"2404.13968","paper":"/paper/protecting-your-llms-with-information","title":"Protecting Your LLMs with Information Bottleneck","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llm-attacks/llm-attacks","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/llm-attacks/llm-attacks/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f556dda0785f3c77","mcp_get_code":{"code_sha256":"f556dda0785f3c77"}},{"arxiv_id":"2404.04125","paper":"/paper/no-zero-shot-without-exponential-data","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bethgelab/frequency_determines_performance","path":"src/retrieval_eval.py","file_url":"https://github.com/bethgelab/frequency_determines_performance/blob/HEAD/src/retrieval_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"507a009866a94a6f","mcp_get_code":{"code_sha256":"507a009866a94a6f"}},{"arxiv_id":"2404.00264","paper":"/paper/dilm-distilling-dataset-into-language-model","title":"DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation","date":"2024-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arumaekawa/dilm","path":"src/coreset/coreset_utils.py","file_url":"https://github.com/arumaekawa/dilm/blob/HEAD/src/coreset/coreset_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"499bced10bfc04a9","mcp_get_code":{"code_sha256":"499bced10bfc04a9"}},{"arxiv_id":"2403.04957","paper":"/paper/automatic-and-universal-prompt-injection","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sheltonliu-n/universal-prompt-injection","path":"utils/opt_utils.py","file_url":"https://github.com/sheltonliu-n/universal-prompt-injection/blob/HEAD/utils/opt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f556dda0785f3c77","mcp_get_code":{"code_sha256":"f556dda0785f3c77"}},{"arxiv_id":"2403.01251","paper":"/paper/accelerating-greedy-coordinate-gradient-via","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaoyiran924/probe-sampling","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/zhaoyiran924/probe-sampling/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db2b1708ea3c49ed","mcp_get_code":{"code_sha256":"db2b1708ea3c49ed"}},{"arxiv_id":"2402.16829","paper":"/paper/gistembed-guided-in-sample-selection-of","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"avsolatorio/gistembed","path":"gist_embed/trainer/loss.py","file_url":"https://github.com/avsolatorio/gistembed/blob/HEAD/gist_embed/trainer/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f91a871ff0d03ed","mcp_get_code":{"code_sha256":"7f91a871ff0d03ed"}},{"arxiv_id":"2402.16459","paper":"/paper/defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihanwang617/llm-jailbreaking-defense-backtranslation","path":"GCG/llm_attacks/base/attack_manager.py","file_url":"https://github.com/yihanwang617/llm-jailbreaking-defense-backtranslation/blob/HEAD/GCG/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"f556dda0785f3c77","mcp_get_code":{"code_sha256":"f556dda0785f3c77"}},{"arxiv_id":"2402.15708","paper":"/paper/query-augmentation-by-decoding-semantics-from","title":"Query Augmentation by Decoding Semantics from Brain Signals","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeziyi1998/brain-query-augmentation","path":"ict/model_utils/model_config.py","file_url":"https://github.com/yeziyi1998/brain-query-augmentation/blob/HEAD/ict/model_utils/model_config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bde4c1a685708c16","mcp_get_code":{"code_sha256":"bde4c1a685708c16"}},{"arxiv_id":"2402.13459","paper":"/paper/learning-to-poison-large-language-models","title":"Learning to Poison Large Language Models for Downstream Manipulation","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rookiezxy/gbtl","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/rookiezxy/gbtl/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a42389ea4ae4a27a","mcp_get_code":{"code_sha256":"a42389ea4ae4a27a"}},{"arxiv_id":"2402.05467","paper":"/paper/rapid-optimization-for-jailbreaking-llms-via","title":"Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"solidshen/ripple_official","path":"src/utils/attack_manager.py","file_url":"https://github.com/solidshen/ripple_official/blob/HEAD/src/utils/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"708a052bc12dad60","mcp_get_code":{"code_sha256":"708a052bc12dad60"}},{"arxiv_id":"2401.17263","paper":"/paper/robust-prompt-optimization-for-defending","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","date":"2024-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lapisrocks/rpo","path":"rpo/opt_utils.py","file_url":"https://github.com/lapisrocks/rpo/blob/HEAD/rpo/opt_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9a3d93b72c5ec034","mcp_get_code":{"code_sha256":"9a3d93b72c5ec034"}},{"arxiv_id":"2401.14578","paper":"/paper/goat-explaining-graph-neural-networks-via","title":"GOAt: Explaining Graph Neural Networks via Graph Output Attribution","date":"2024-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sluxsr/GOAt","path":"node_classi_plot_pack/nc_plots.py","file_url":"https://github.com/sluxsr/GOAt/blob/HEAD/node_classi_plot_pack/nc_plots.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ddb0751a34af6db","mcp_get_code":{"code_sha256":"1ddb0751a34af6db"}},{"arxiv_id":"2312.04103","paper":"/paper/enhancing-the-rationale-input-alignment-for","title":"Enhancing the Rationale-Input Alignment for Self-explaining Rationalization","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jugechengzi/dar","path":"embedding.py","file_url":"https://github.com/jugechengzi/dar/blob/HEAD/embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7fd4428a7a26977","mcp_get_code":{"code_sha256":"a7fd4428a7a26977"}},{"arxiv_id":"2311.09948","paper":"/paper/hijacking-large-language-models-via","title":"Hijacking Large Language Models via Adversarial In-Context Learning","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RookieZxy/GGI-attack","path":"GGI-attack/llm_attacks/base/attack_manager.py","file_url":"https://github.com/RookieZxy/GGI-attack/blob/HEAD/GGI-attack/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"33377834cc7d0c84","mcp_get_code":{"code_sha256":"33377834cc7d0c84"}},{"arxiv_id":"2310.15140","paper":"/paper/autodan-automatic-and-interpretable","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rotaryhammer/code-autodan","path":"autodan/autodan/attack_manager.py","file_url":"https://github.com/rotaryhammer/code-autodan/blob/HEAD/autodan/autodan/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"01abe3bd48ba14fc","mcp_get_code":{"code_sha256":"01abe3bd48ba14fc"}},{"arxiv_id":"2309.13391","paper":"/paper/d-separation-for-causal-self-explanation-1","title":"D-Separation for Causal Self-Explanation","date":"2023-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jugechengzi/Rationalization-MCD","path":"embedding.py","file_url":"https://github.com/jugechengzi/Rationalization-MCD/blob/HEAD/embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7fd4428a7a26977","mcp_get_code":{"code_sha256":"a7fd4428a7a26977"}},{"arxiv_id":"2308.11804","paper":"/paper/ceci-n-est-pas-une-pomme-adversarial","title":"Adversarial Illusions in Multi-Modal Embeddings","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ebagdasa/adversarial_illusions","path":"dataset_utils.py","file_url":"https://github.com/ebagdasa/adversarial_illusions/blob/HEAD/dataset_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"996d7797acf3500c","mcp_get_code":{"code_sha256":"996d7797acf3500c"}},{"arxiv_id":"2307.00175","paper":"/paper/still-no-lie-detector-for-language-models","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","date":"2023-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"balevinstein/probes","path":"Train_CCSProbe.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/Train_CCSProbe.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1fd11bf75e70a151","mcp_get_code":{"code_sha256":"1fd11bf75e70a151"}},{"arxiv_id":"2305.17826","paper":"/paper/notable-transferable-backdoor-attacks-against","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","date":"2023-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ru-system-software-and-security/notable","path":"autoprompt/create_trigger.py","file_url":"https://github.com/ru-system-software-and-security/notable/blob/HEAD/autoprompt/create_trigger.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20a9293a820f617d","mcp_get_code":{"code_sha256":"20a9293a820f617d"}},{"arxiv_id":"2305.17331","paper":"/paper/augmentation-adapted-retriever-improves","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/chatgpt-retrieval-plugin","path":"services/openai.py","file_url":"https://github.com/openai/chatgpt-retrieval-plugin/blob/HEAD/services/openai.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b009eb83df585f1c","mcp_get_code":{"code_sha256":"b009eb83df585f1c"}},{"arxiv_id":"2305.00650","paper":"/paper/discover-and-cure-concept-aware-mitigation-of","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","date":"2023-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Wuyxin/DISC","path":"disc/concept_utils/cav_utils.py","file_url":"https://github.com/Wuyxin/DISC/blob/HEAD/disc/concept_utils/cav_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87689c095e68cee7","mcp_get_code":{"code_sha256":"87689c095e68cee7"}},{"arxiv_id":"2302.14691","paper":"/paper/in-context-instruction-learning","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","date":"2023-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seonghyeonye/icil","path":"src/run_nearest_demo.py","file_url":"https://github.com/seonghyeonye/icil/blob/HEAD/src/run_nearest_demo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73680032c6cc1a34","mcp_get_code":{"code_sha256":"73680032c6cc1a34"}},{"arxiv_id":"2203.10581","paper":"/paper/cluster-tune-boost-cold-start-performance-in","title":"Cluster & Tune: Boost Cold Start Performance in Text Classification","date":"2022-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/intermediate-training-using-clustering","path":"run_experiment.py","file_url":"https://github.com/ibm/intermediate-training-using-clustering/blob/HEAD/run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c1fcf89801c4ea9e","mcp_get_code":{"code_sha256":"c1fcf89801c4ea9e"}},{"arxiv_id":"2112.15594","paper":"/paper/a-neural-network-solves-and-generates","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","date":"2021-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idrori/mathq","path":"code/embedding.py","file_url":"https://github.com/idrori/mathq/blob/HEAD/code/embedding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"caf8168c846f56d5","mcp_get_code":{"code_sha256":"caf8168c846f56d5"}},{"arxiv_id":"2110.08552","paper":"/paper/virtual-augmentation-supported-contrastive","title":"Virtual Augmentation Supported Contrastive Learning of Sentence Representations","date":"2021-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/sentence-representations","path":"DownstreamEval/clustering/clustering_eval.py","file_url":"https://github.com/amazon-science/sentence-representations/blob/HEAD/DownstreamEval/clustering/clustering_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"13e3886c6d762ec6","mcp_get_code":{"code_sha256":"13e3886c6d762ec6"}},{"arxiv_id":"2010.15980","paper":"/paper/autoprompt-eliciting-knowledge-from-language","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","date":"2020-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucinlp/autoprompt","path":"autoprompt/create_trigger.py","file_url":"https://github.com/ucinlp/autoprompt/blob/HEAD/autoprompt/create_trigger.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"20a9293a820f617d","mcp_get_code":{"code_sha256":"20a9293a820f617d"}},{"arxiv_id":"2007.06225","paper":"/paper/prottrans-towards-cracking-the-language-of","title":"ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2020-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agemagician/ProtTrans","path":"Embedding/prott5_embedder.py","file_url":"https://github.com/agemagician/ProtTrans/blob/HEAD/Embedding/prott5_embedder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd492312bc93c287","mcp_get_code":{"code_sha256":"dd492312bc93c287"}},{"arxiv_id":"1909.01300","paper":"/paper/the-oxford-radar-robotcar-dataset-a-radar","title":"The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset","date":null,"month_inferred_from_arxiv_id":"2019-09","title_source":"archive","repo":"mttgdd/oord-dataset","path":"src/compute_distance_matrix.py","file_url":"https://github.com/mttgdd/oord-dataset/blob/HEAD/src/compute_distance_matrix.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"adbf95aba4ffd8f5","mcp_get_code":{"code_sha256":"adbf95aba4ffd8f5"}},{"arxiv_id":"1502.03044","paper":"/paper/show-attend-and-tell-neural-image-caption","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","date":"2015-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LinXueyuanStdio/LaTeX_OCR","path":"model/decoder.py","file_url":"https://github.com/LinXueyuanStdio/LaTeX_OCR/blob/HEAD/model/decoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b24ffeda92bc6e1","mcp_get_code":{"code_sha256":"9b24ffeda92bc6e1"}},{"arxiv_id":"aaai_16580","paper":null,"title":"arXiv:aaai_16580","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"modriczhang/HRL-Rec","path":"layer_util.py","file_url":"https://github.com/modriczhang/HRL-Rec/blob/HEAD/layer_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fb6bc9cda68a32c1","mcp_get_code":{"code_sha256":"fb6bc9cda68a32c1"}},{"arxiv_id":"2024.findings-naacl.294","paper":null,"title":"arXiv:2024.findings-naacl.294","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"balevinstein/Probes","path":"Train_CCSProbe.py","file_url":"https://github.com/balevinstein/Probes/blob/HEAD/Train_CCSProbe.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1fd11bf75e70a151","mcp_get_code":{"code_sha256":"1fd11bf75e70a151"}},{"arxiv_id":"2024.findings-naacl.294","paper":null,"title":"arXiv:2024.findings-naacl.294","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"balevinstein/Probes","path":"Generate_CCS_predictions.py","file_url":"https://github.com/balevinstein/Probes/blob/HEAD/Generate_CCS_predictions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4680e27c1f698ff","mcp_get_code":{"code_sha256":"e4680e27c1f698ff"}},{"arxiv_id":"2024.findings-naacl.199","paper":null,"title":"arXiv:2024.findings-naacl.199","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"arumaekawa/DiLM","path":"src/coreset/coreset_utils.py","file_url":"https://github.com/arumaekawa/DiLM/blob/HEAD/src/coreset/coreset_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"499bced10bfc04a9","mcp_get_code":{"code_sha256":"499bced10bfc04a9"}},{"arxiv_id":"2023.acl-long.426","paper":null,"title":"arXiv:2023.acl-long.426","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"umanlp/babelbert","path":"utils/functions.py","file_url":"https://github.com/umanlp/babelbert/blob/HEAD/utils/functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4ebe45034029f9ba","mcp_get_code":{"code_sha256":"4ebe45034029f9ba"}}]}