No article text was recorded for this version.
black-box API constraints
Version 1 of 1197 papers205 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Knowledge Distillation of Large Language Models
- Blog: Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
- Blog: A Survey on LLM Inference-Time Self-Improvement
- Blog: Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning
- Blog: CPT: Consistent Proxy Tuning for Black-box Optimization
- Blog: When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs
- Blog: Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking
- Blog: Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
- Blog: Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors
- Blog: Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs
- Blog: Weak-to-Strong Jailbreaking on Large Language Models
- Blog: Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
- Blog: Scaling of Class-wise Training Losses for Post-hoc Calibration
- Blog: Are LLMs Aware that Some Questions are not Open-ended?
- Blog: BetterV: Controlled Verilog Generation with Discriminative Guidance
- Blog: Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
- Blog: ToDi: Token-wise Distillation via Fine-Grained Divergence Control
- Blog: Scaling of Class-wise Training Losses for Post-hoc Calibration
- Blog: Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes
- Blog: Every Language Model Has a Forgery-Resistant Signature
- Blog: Demonstration Augmentation for Zero-shot In-context Learning
- Blog: LLMR: Knowledge Distillation with a Large Language Model-Induced Reward
- Blog: Who can we trust? LLM-as-a-jury for Comparative Assessment
- Blog: TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge
- Blog: Guiding Large Language Models for Biomedical Entity Linking via Restrictive and Contrastive Decoding
- Blog: daDPO: Distribution-Aware DPO for Distilling Conversational Abilities
- Blog: Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
- Blog: Prompt Sketching for Large Language Models
- Blog: Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
- Blog: Advanced Black-Box Tuning of Large Language Models with Limited API Calls
- Blog: Mixtures of In-Context Learners
- Blog: Multi-Personality Generation of LLMs at Decoding-time
- Blog: Clustering and Median Aggregation Improve Differentially Private Inference
- Blog: Type-Constrained Code Generation with Language Models
- Blog: Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
- Blog: AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
- Blog: Improving Logits-based Detector without Logits from Black-box LLMs
- Blog: Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
- Blog: KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection
- Blog: DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
- Blog: TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
- Blog: Cognitive Constraint Simulation and the Geometry of Human Authorship: A First-Principles Theory of AI Text Detection
- Blog: USCD: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding
- Blog: PostMark: A Robust Blackbox Watermark for Large Language Models
- Blog: LOTUS: Enabling Semantic Queries with LLMs Over Tables of Unstructured and Structured Data
- Blog: Single-pass Detection of Jailbreaking Input in Large Language Models
- Blog: TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
- Blog: Flexible Grammar-Based Constrained Decoding for Language Models
- Blog: Every Language Model Has a Forgery-Resistant Signature
- Blog: Extracting Prompts by Inverting LLM Outputs
- Blog: Prompting Is Programming: A Query Language For Large Language Models
- Blog: An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation
- Blog: Logits are All We Need to Adapt Closed Models
- Blog: Mixture-of-Personas Language Models for Population Simulation
- Blog: PAL: Proxy-Guided Black-Box Attack on Large Language Models
- Blog: Learning to Decode Collaboratively with Multiple Language Models
- Blog: Mechanism Design for Large Language Models (Extended Abstract)
- Blog: CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
- Blog: Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning
- Blog: Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
Showing 60 of 197 papers.
History & citation
Current · Permanent link
- Decoding-time Steering via Logit Manipulation merged into this direction (84% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_black_box_api_constraints_ff1d180e,
title = {black-box API constraints},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/black-box-api-constraints/rdr_ff1d180ee0f64dd2b6eb1c0e5058342e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_black_box_api_constraints_ff1d180e_v1,
title = {black-box API constraints},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/black-box-api-constraints/rdr_ff1d180ee0f64dd2b6eb1c0e5058342e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}