{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/instruction-following/papers/10","list_of":"/task/instruction-following","task":"Instruction Following","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":10,"pages_in_order":12,"rows_per_page":100,"rows":[901,1000],"of":1135,"counts":{"archive_papers_tagged":1135,"with_a_code_link":609,"where_syntology_ran_a_sample":311,"not_listed_spam_title":0,"listed":1135,"listed_where_code_ran":311,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":255,"every_run_a_failure_of_syntologys_instrument":56,"listed_with_a_run_with_no_instrument_failure":255,"listed_every_run_a_failure_of_syntologys_instrument":56,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/instruction-following","prev":"/task/instruction-following/papers/9","next":"/task/instruction-following/papers/11","papers":[{"url":null,"slug":"beyond-instruction-following-evaluating-rule","title":"Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models","date":"2024-07-11","arxiv_id":"2407.08440","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-empowered-multi-modal-representation","title":"LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition","date":"2024-07-09","arxiv_id":"2407.06730","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-as-an-assignment","title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","date":"2024-07-07","arxiv_id":"2407.05216","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-and-fine-grained-instruction","title":"Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data","date":"2024-07-04","arxiv_id":"2407.03942","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-rax-domain-specific-radiologic-assistant","title":"D-Rax: Domain-specific Radiologic assistant leveraging multi-modal data and eXpert model predictions","date":"2024-07-02","arxiv_id":"2407.02604","repositories_listed":0,"syntology":null},{"url":null,"slug":"pelican-correcting-hallucination-in-vision","title":"Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification","date":"2024-07-02","arxiv_id":"2407.02352","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-multilingual-instruction-finetuning","title":"Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets","date":"2024-07-01","arxiv_id":"2407.01853","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-data-augmentation-with-large","title":"Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysis","date":"2024-06-29","arxiv_id":"2407.00341","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalebio-scalable-bilevel-optimization-for","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","date":"2024-06-28","arxiv_id":"2406.19976","repositories_listed":0,"syntology":null},{"url":null,"slug":"desta-enhancing-speech-language-models","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","date":"2024-06-27","arxiv_id":"2406.18871","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnijarvis-unified-vision-language-action","title":"OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents","date":"2024-06-27","arxiv_id":"2407.00114","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-play-zero-shot-prompting-with-large","title":"Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation","date":"2024-06-26","arxiv_id":"2406.18460","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-text-is-worth-several-tokens-text-embedding","title":"A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens","date":"2024-06-25","arxiv_id":"2406.17378","repositories_listed":0,"syntology":null},{"url":null,"slug":"following-length-constraints-in-instructions","title":"Following Length Constraints in Instructions","date":"2024-06-25","arxiv_id":"2406.17744","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-instruction-following-ability","title":"Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation","date":"2024-06-24","arxiv_id":"2406.16356","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-better-or-show-smarter-on-instructions","title":"Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization","date":"2024-06-22","arxiv_id":"2406.15708","repositories_listed":0,"syntology":null},{"url":null,"slug":"dem-distribution-edited-model-for-training","title":"DEM: Distribution Edited Model for Training with Mixed Data Distributions","date":"2024-06-21","arxiv_id":"2406.15570","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-batch-analysis-for-adagrad-under","title":"AdaGrad under Anisotropic Smoothness","date":"2024-06-21","arxiv_id":"2406.15244","repositories_listed":0,"syntology":null},{"url":null,"slug":"ical-continual-learning-of-multimodal-agents","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","date":"2024-06-20","arxiv_id":"2406.14596","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-catastrophic-forgetting-of","title":"Refine Large Language Model Fine-tuning via Instruction Vector","date":"2024-06-18","arxiv_id":"2406.12227","repositories_listed":0,"syntology":null},{"url":null,"slug":"prepair-pointwise-reasoning-enhance-pairwise","title":"The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators","date":"2024-06-18","arxiv_id":"2406.12319","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-flaws-exploring-imperfections","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","date":"2024-06-18","arxiv_id":"2406.12397","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-instruction-following-in-unknown","title":"Embodied Instruction Following in Unknown Environments","date":"2024-06-17","arxiv_id":"2406.11818","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-far-can-in-context-alignment-go-exploring","title":"How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment","date":"2024-06-17","arxiv_id":"2406.11474","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-and-testing-instruction-following","title":"Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants","date":"2024-06-17","arxiv_id":"2406.11301","repositories_listed":0,"syntology":null},{"url":null,"slug":"reminding-multimodal-large-language-models-of","title":"Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags","date":"2024-06-16","arxiv_id":"2406.10839","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-visual-instruction-tuning","title":"Comparison Visual Instruction Tuning","date":"2024-06-13","arxiv_id":"2406.09240","repositories_listed":0,"syntology":null},{"url":null,"slug":"discreteslu-a-large-language-model-with-self","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","date":"2024-06-13","arxiv_id":"2406.09345","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-user-data-on-mitigating-fine-tuning","title":"Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models","date":"2024-06-12","arxiv_id":"2406.10288","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-properties-identifying-challenges-in-dpo","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","date":"2024-06-11","arxiv_id":"2406.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"facegpt-self-supervised-learning-to-chat","title":"FaceGPT: Self-supervised Learning to Chat about 3D Human Faces","date":"2024-06-11","arxiv_id":"2406.07163","repositories_listed":0,"syntology":null},{"url":null,"slug":"optune-efficient-online-preference-tuning","title":"OPTune: Efficient Online Preference Tuning","date":"2024-06-11","arxiv_id":"2406.07657","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructing-prompt-to-prompt-generation-for","title":"Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning","date":"2024-06-05","arxiv_id":"2406.03032","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-ensembling-for-mitigating-reward","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","date":"2024-06-03","arxiv_id":"2406.01013","repositories_listed":0,"syntology":null},{"url":null,"slug":"lidao-towards-limited-interventions-for","title":"LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models","date":"2024-06-01","arxiv_id":"2406.00548","repositories_listed":0,"syntology":null},{"url":null,"slug":"clembench-2024-a-challenging-dynamic","title":"clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents","date":"2024-05-31","arxiv_id":"2405.20859","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-reward-models-with-synthetic","title":"Improving Reward Models with Synthetic Critiques","date":"2024-05-31","arxiv_id":"2405.20850","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-embeddings-for-graph-instruction-tuning","title":"Joint Embeddings for Graph Instruction Tuning","date":"2024-05-31","arxiv_id":"2405.20684","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructioncp-a-fast-approach-to-transfer","title":"InstructionCP: A fast approach to transfer Large Language Models into target language","date":"2024-05-30","arxiv_id":"2405.20175","repositories_listed":0,"syntology":null},{"url":null,"slug":"nadine-an-llm-driven-intelligent-social-robot","title":"Nadine: An LLM-driven Intelligent Social Robot with Affective Capabilities and Human-like Memory","date":"2024-05-30","arxiv_id":"2405.20189","repositories_listed":0,"syntology":null},{"url":"/paper/sam-e-leveraging-visual-foundation-model-with","slug":"sam-e-leveraging-visual-foundation-model-with","title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","date":"2024-05-30","arxiv_id":"2405.19586","repositories_listed":0,"syntology":null},{"url":null,"slug":"ts-align-a-teacher-student-collaborative","title":"TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models","date":"2024-05-30","arxiv_id":"2405.20215","repositories_listed":0,"syntology":null},{"url":null,"slug":"blsp-kd-bootstrapping-language-speech-pre","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","date":"2024-05-29","arxiv_id":"2405.19041","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-vila-cross-modality-alignment-for-large","title":"X-VILA: Cross-Modality Alignment for Large Language Model","date":"2024-05-29","arxiv_id":"2405.19335","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-corrected-multimodal-large-language","title":"Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation","date":"2024-05-27","arxiv_id":"2405.17418","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-role-play-to-drama-interaction-an-llm","title":"From Role-Play to Drama-Interaction: An LLM Solution","date":"2024-05-23","arxiv_id":"2405.14231","repositories_listed":0,"syntology":null},{"url":null,"slug":"re-adapt-reverse-engineered-adaptation-of","title":"RE-Adapt: Reverse Engineered Adaptation of Large Language Models","date":"2024-05-23","arxiv_id":"2405.15007","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-instruction-following-abilities-of","title":"Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning","date":"2024-05-22","arxiv_id":"2405.13448","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-large-vision-language-models-as","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","date":"2024-05-16","arxiv_id":"2405.10292","repositories_listed":0,"syntology":null},{"url":null,"slug":"speechguard-exploring-the-adversarial","title":"SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models","date":"2024-05-14","arxiv_id":"2405.08317","repositories_listed":0,"syntology":null},{"url":null,"slug":"speechverse-a-large-scale-generalizable-audio","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","date":"2024-05-14","arxiv_id":"2405.08295","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-context-alignment-with-short","title":"Long Context Alignment with Short Instructions and Synthesized Positions","date":"2024-05-07","arxiv_id":"2405.03939","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-high-sparsity-foundational-llama","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment","date":"2024-05-06","arxiv_id":"2405.03594","repositories_listed":0,"syntology":null},{"url":null,"slug":"flame-factuality-aware-alignment-for-large","title":"FLAME: Factuality-Aware Alignment for Large Language Models","date":"2024-05-02","arxiv_id":"2405.01525","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-ad-large-language-model-based-audio","title":"LLM-AD: Large Language Model based Audio Description System","date":"2024-05-02","arxiv_id":"2405.00983","repositories_listed":0,"syntology":null},{"url":null,"slug":"wildchat-1m-chatgpt-interaction-logs-in-the","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","date":"2024-05-02","arxiv_id":"2405.01470","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-fact-checker-enabling-high-fidelity","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","date":"2024-04-30","arxiv_id":"2404.19752","repositories_listed":0,"syntology":null},{"url":null,"slug":"helper-x-a-unified-instructable-embodied","title":"HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models","date":"2024-04-29","arxiv_id":"2404.19065","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-persona-to-personalization-a-survey-on","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","date":"2024-04-28","arxiv_id":"2404.18231","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-layout-planning-for-visually-rich","title":"Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Models","date":"2024-04-23","arxiv_id":"2404.15271","repositories_listed":0,"syntology":null},{"url":null,"slug":"socratic-planner-inquiry-based-zero-shot","title":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following","date":"2024-04-21","arxiv_id":"2404.15190","repositories_listed":0,"syntology":null},{"url":null,"slug":"eyes-can-deceive-benchmarking-counterfactual","title":"Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning","date":"2024-04-19","arxiv_id":"2404.12966","repositories_listed":0,"syntology":null},{"url":null,"slug":"closed-loop-open-vocabulary-mobile","title":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","date":"2024-04-16","arxiv_id":"2404.10220","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-misuse-potential-of-base-large","title":"Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning","date":"2024-04-16","arxiv_id":"2404.10552","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-plan-generalize-continual-few-shot","title":"Sketch-Plan-Generalize: Learning and Planning with Neuro-Symbolic Programmatic Representations for Inductive Spatial Concepts","date":"2024-04-11","arxiv_id":"2404.07774","repositories_listed":0,"syntology":null},{"url":null,"slug":"codeclm-aligning-language-models-with","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","date":"2024-04-08","arxiv_id":"2404.05875","repositories_listed":0,"syntology":null},{"url":null,"slug":"ferret-ui-grounded-mobile-ui-understanding","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","date":"2024-04-08","arxiv_id":"2404.05719","repositories_listed":0,"syntology":null},{"url":null,"slug":"canttalkaboutthis-aligning-language-models-to","title":"CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues","date":"2024-04-04","arxiv_id":"2404.03820","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-incomplete-loop-deductive-inductive-and","title":"An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models","date":"2024-04-03","arxiv_id":"2404.03028","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperclova-x-technical-report","title":"HyperCLOVA X Technical Report","date":"2024-04-02","arxiv_id":"2404.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-excitor-general-instruction-tuning-via","title":"LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction","date":"2024-04-01","arxiv_id":"2404.00913","repositories_listed":0,"syntology":null},{"url":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","repositories_listed":0,"syntology":null},{"url":"/paper/plug-and-play-grounding-of-reasoning-in","slug":"plug-and-play-grounding-of-reasoning-in","title":"Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models","date":"2024-03-28","arxiv_id":"2403.19322","repositories_listed":0,"syntology":null},{"url":null,"slug":"argument-quality-assessment-in-the-age-of","title":"Argument Quality Assessment in the Age of Instruction-Following Large Language Models","date":"2024-03-24","arxiv_id":"2403.16084","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-dialogue-strategy-learning-for","title":"Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning","date":"2024-03-23","arxiv_id":"2403.15737","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-robustness-of-large-language","title":"Improving the Robustness of Large Language Models via Consistency Alignment","date":"2024-03-21","arxiv_id":"2403.14221","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualcritic-making-lmms-perceive-visual","title":"VisualCritic: Making LMMs Perceive Visual Quality Like Humans","date":"2024-03-19","arxiv_id":"2403.12806","repositories_listed":0,"syntology":null},{"url":null,"slug":"wolf-large-language-model-framework-for-cxr","title":"WoLF: Wide-scope Large Language Model Framework for CXR Understanding","date":"2024-03-19","arxiv_id":"2403.15456","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-half-listen-capturing-key-part","title":"Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning","date":"2024-03-15","arxiv_id":"2403.10056","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-dialogue-hallucination-for-large","title":"Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning","date":"2024-03-15","arxiv_id":"2403.10492","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffchat-learning-to-chat-with-text-to-image","title":"DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation","date":"2024-03-08","arxiv_id":"2403.04997","repositories_listed":0,"syntology":null},{"url":null,"slug":"cotbal-comprehensive-task-balancing-for-multi","title":"CoTBal: Comprehensive Task Balancing for Multi-Task Visual Instruction Tuning","date":"2024-03-07","arxiv_id":"2403.04343","repositories_listed":0,"syntology":null},{"url":null,"slug":"kiwi-a-dataset-of-knowledge-intensive-writing","title":"KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions","date":"2024-03-06","arxiv_id":"2403.03866","repositories_listed":0,"syntology":null},{"url":null,"slug":"cogenesis-a-framework-collaborating-large-and","title":"CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following","date":"2024-03-05","arxiv_id":"2403.03129","repositories_listed":0,"syntology":null},{"url":null,"slug":"opex-a-component-wise-analysis-of-llm-centric","title":"OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following","date":"2024-03-05","arxiv_id":"2403.03017","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-decoding-of-critical-tokens-for","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","date":"2024-02-28","arxiv_id":"2402.17982","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-big-generate-quick-llm-to-slm-for-fast","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","date":"2024-02-26","arxiv_id":"2402.16844","repositories_listed":0,"syntology":null},{"url":null,"slug":"navid-video-based-vlm-plans-the-next-step-for","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","date":"2024-02-24","arxiv_id":"2402.15852","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-enhances-existing-mechanisms-a","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","date":"2024-02-22","arxiv_id":"2402.14811","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-cross-lingual-transfer-in","title":"Zero-shot cross-lingual transfer in instruction tuning of large language models","date":"2024-02-22","arxiv_id":"2402.14778","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-multilingual-instruction-tuning","title":"Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions?","date":"2024-02-21","arxiv_id":"2402.13703","repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-trojan-multimodal-instruction-backdoor","title":"VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models","date":"2024-02-21","arxiv_id":"2402.13851","repositories_listed":0,"syntology":null},{"url":null,"slug":"cif-bench-a-chinese-instruction-following","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models","date":"2024-02-20","arxiv_id":"2402.13109","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-almost-from-scratch","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","date":"2024-02-20","arxiv_id":"2402.13064","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-causal-language-models","title":"Transformer-based Causal Language Models Perform Clustering","date":"2024-02-19","arxiv_id":"2402.12151","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-for-prompt-learning","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","date":"2024-02-15","arxiv_id":"2402.09723","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-query-focused-disaster-summarization","title":"Multi-Query Focused Disaster Summarization via Instruction-Based Prompting","date":"2024-02-14","arxiv_id":"2402.09008","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-impact-of-data","title":"Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation","date":"2024-02-12","arxiv_id":"2402.08100","repositories_listed":0,"syntology":null},{"url":null,"slug":"pivot-iterative-visual-prompting-elicits","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","date":"2024-02-12","arxiv_id":"2402.07872","repositories_listed":0,"syntology":null},{"url":null,"slug":"nevermind-instruction-override-and-moderation","title":"Nevermind: Instruction Override and Moderation in Large Language Models","date":"2024-02-05","arxiv_id":"2402.03303","repositories_listed":0,"syntology":null}],"record_sha256":"0a494efd65a3784a07137877f768e09393b13e24e103e4a0440b9a0375041327","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}