AGORA is an inference-free step-level compressor for LLM agent prompts that retains at least 75% of uncompressed performance in most tested settings where token-level methods collapse due to action-grammar destruction.
Let me speak freely? a study on the impact of format restrictions on performance of large language models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Schema-key wording functions as an implicit instruction channel under constrained decoding, with experiments showing that rephrasing only the keys can substantially change accuracy on math benchmarks while prompt, model, structure, and decoding remain unchanged.
AloLab, an iterative meta-agent prompt optimizer, raises structured output accuracy for 7-9B models from 0% to 84-87% on GSM8K while preserving near-native inference speed.
LLMs leak up to 23 percentage points more PII to AI agents than humans, attributed to inactive safety attention heads in 3,464 tested interactions.
LLMs prefer institutionally corroborated sources in knowledge conflicts but repetition from weaker sources reverses this preference, and a new mitigation method reduces repetition bias by up to 79% while retaining most original preferences.
Introduces IFBench benchmark with 58 new constraints and demonstrates RLVR training improves generalization of language models to unseen verifiable output constraints.
Empirical benchmarks on four SE tasks show grammar-constrained decoding and TTMG eliminate most syntax errors in LLM outputs while structural and semantic errors persist and cascade in downstream tools.
SLMs achieve competitive performance with LLMs on pedagogically grounded metrics for assessment design but exhibit biases in model-based evaluation versus experts, supporting bounded AI use with human oversight.
ADAM uses personality-guided LLM augmentation and cross-lingual attention distillation to raise balanced accuracy on multilingual personality recognition to 0.6332 on Essays and 0.7448 on Kaggle, outperforming standard BCE loss.
Longer textual reasoning chains degrade MLLM accuracy on fine-grained visual tasks; a new normalization and constrained-reward training framework mitigates the effect and sets new SOTA numbers.
Introduces a migration framework and A/B/C taxonomy to convert static expert LLM workflows into self-evolution-ready harnesses.
citing papers explorer
-
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
AGORA is an inference-free step-level compressor for LLM agent prompts that retains at least 75% of uncompressed performance in most tested settings where token-level methods collapse due to action-grammar destruction.
-
Schema Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding
Schema-key wording functions as an implicit instruction channel under constrained decoding, with experiments showing that rephrasing only the keys can substantially change accuracy on math benchmarks while prompt, model, structure, and decoding remain unchanged.
-
When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models
AloLab, an iterative meta-agent prompt optimizer, raises structured output accuracy for 7-9B models from 0% to 84-87% on GSM8K while preserving near-native inference speed.
-
The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans
LLMs leak up to 23 percentage points more PII to AI agents than humans, attributed to inactive safety attention heads in 3,464 tested interactions.
-
Whose Facts Win? LLM Source Preferences under Knowledge Conflicts
LLMs prefer institutionally corroborated sources in knowledge conflicts but repetition from weaker sources reverses this preference, and a new mitigation method reduces repetition bias by up to 79% while retaining most original preferences.
-
Generalizing Verifiable Instruction Following
Introduces IFBench benchmark with 58 new constraints and demonstrates RLVR training improves generalization of language models to unseen verifiable output constraints.
-
Empirical Study for Structured Output Control in LLMs for Software Engineering
Empirical benchmarks on four SE tasks show grammar-constrained decoding and TTMG eliminate most syntax errors in LLM outputs while structural and semantic errors persist and cascade in downstream tools.
-
Small, Private Language Models as Teammates for Educational Assessment Design
SLMs achieve competitive performance with LLMs on pedagogically grounded metrics for assessment design but exhibit biases in model-based evaluation versus experts, supporting bounded AI use with human oversight.
-
Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition
ADAM uses personality-guided LLM augmentation and cross-lingual attention distillation to raise balanced accuracy on multilingual personality recognition to 0.6332 on Essays and 0.7448 on Kaggle, outperforming standard BCE loss.
-
Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?
Longer textual reasoning chains degrade MLLM accuracy on fine-grained visual tasks; a new normalization and constrained-reward training framework mitigates the effect and sets new SOTA numbers.
-
Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines
Introduces a migration framework and A/B/C taxonomy to convert static expert LLM workflows into self-evolution-ready harnesses.