ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
Automatic Prompt Optimization with ``Gradient Descent'' and Beam Search
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
PQR is a dual-module iterative framework that generates diverse and realistic queries to elicit failures in QA agents, detecting 23-78% more unhelpful responses than prior methods.
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
BrainROI achieves leading cross-subject brain-captioning results on NSD by combining multi-atlas soft-ROI fusion with interpretable prompt optimization.
JTPRO co-optimizes prompts and tool descriptions via reflection to raise overall success rate by 5-20% over baselines on multi-tool benchmarks.
citing papers explorer
-
ORPO: Monolithic Preference Optimization without Reference Model
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
-
PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures
PQR is a dual-module iterative framework that generates diverse and realistic queries to elicit failures in QA agents, detecting 23-78% more unhelpful responses than prior methods.
-
TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
-
Unified Multimodal Brain Decoding via Cross-Subject Soft-ROI Fusion
BrainROI achieves leading cross-subject brain-captioning results on NSD by combining multi-atlas soft-ROI fusion with interpretable prompt optimization.
-
JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
JTPRO co-optimizes prompts and tool descriptions via reflection to raise overall success rate by 5-20% over baselines on multi-tool benchmarks.
- iPOE: Interpretable Prompt Optimization via Explanations