R2IF improves LLM function-calling accuracy by up to 34.62% on BFCL using a composite reward system with CER and SMV components optimized via GRPO, while increasing interpretability through positive CoT effectiveness.
Advances in Neural Information Processing Systems (NeurIPS) , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
A single consistency instruction with harmful prior actions causes aligned frontier LLMs to select unsafe options at 91-98% rates in high-stakes domains, with escalation and inverse scaling by model size.
citing papers explorer
-
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling
R2IF improves LLM function-calling accuracy by up to 34.62% on BFCL using a composite reward system with CER and SMV components optimized via GRPO, while increasing interpretability through positive CoT effectiveness.
-
Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
-
History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions
A single consistency instruction with harmful prior actions causes aligned frontier LLMs to select unsafe options at 91-98% rates in high-stakes domains, with escalation and inverse scaling by model size.