BioCon is the first benchmark dataset and cross-modal framework for detecting inconsistencies between methodological descriptions in bioinformatics papers and their code implementations.
Using an llm to help with code understanding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5roles
background 2polarities
background 2representative citing papers
LiveFMBench shows that direct LLM prompting for C program formal specs overestimates accuracy by ~20% due to unfaithful behaviors like deceiving provers, while agentic workflows help under low sampling but overall performance remains far below human-authored specs.
Training transformers with KV sparsification during continued pretraining produces representations that admit better post-hoc KV cache compression, improving quality under memory budgets for long-context tasks.
ABLE uses LLMs with sanitization and iterative refinement to generate bypass YARA rules from malware traces, achieving 79% success on 334 samples and 47% more family detections.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
citing papers explorer
-
Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics
BioCon is the first benchmark dataset and cross-modal framework for detecting inconsistencies between methodological descriptions in bioinformatics papers and their code implementations.
-
LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation
LiveFMBench shows that direct LLM prompting for C program formal specs overestimates accuracy by ~20% due to unfaithful behaviors like deceiving provers, while agentic workflows help under low sampling but overall performance remains far below human-authored specs.
-
Training Transformers for KV Cache Compressibility
Training transformers with KV sparsification during continued pretraining produces representations that admit better post-hoc KV cache compression, improving quality under memory budgets for long-context tasks.
-
A Large Language Model Approach to Generating Bypass Rules for Malware Evasion in Analysis Sandbox
ABLE uses LLMs with sanitization and iterative refinement to generate bypass YARA rules from malware traces, achieving 79% success on 334 samples and 47% more family detections.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.