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.
hub
Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
Prefix gain measured via student-model solve-rate improvement is used to train a Prefix Utility Model (PUM) that supplies stronger supervision than correctness-based process rewards for mathematical reasoning.
A panel of smaller diverse LLMs outperforms a single large model as an evaluator of generations, showing less intra-model bias and over 7x lower cost.
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
Decisive combines document-grounded option scoring with adaptive Bayesian preference elicitation to achieve up to 20% higher decision accuracy than LLMs and existing frameworks across domains.
Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
ProbScale finds layer subsets in SLMs like RoBERTa-Large and T5-Base that cut parameters 5-10x while retaining 95-98% of original task performance by maximizing aggregated probe scores under a budget.
AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.
LLM-extracted patterns merging logical structures and linguistic cues yield statistically significant gains in fallacy classification over zero-shot baselines with cross-dataset generalization.
MMoA adds LSTM recurrence to Mixture-of-Agents routing, reaching 58.0% win rate on AlpacaEval 2.0 versus 59.8% for baseline MoA while cutting runtime by up to 4.6%.
Fine-tuned PEGASUS achieves state-of-the-art ROUGE scores on XL-Sum English corpus with 4.04% ROUGE-1, 15.25% ROUGE-2, and 3.39% ROUGE-L gains over mT5 baseline.
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.
-
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning
Prefix gain measured via student-model solve-rate improvement is used to train a Prefix Utility Model (PUM) that supplies stronger supervision than correctness-based process rewards for mathematical reasoning.
-
Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
A panel of smaller diverse LLMs outperforms a single large model as an evaluator of generations, showing less intra-model bias and over 7x lower cost.
-
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
-
Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents
Decisive combines document-grounded option scoring with adaptive Bayesian preference elicitation to achieve up to 20% higher decision accuracy than LLMs and existing frameworks across domains.
-
Steering Llama 2 via Contrastive Activation Addition
Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference
ProbScale finds layer subsets in SLMs like RoBERTa-Large and T5-Base that cut parameters 5-10x while retaining 95-98% of original task performance by maximizing aggregated probe scores under a budget.
-
AppAgent: Multimodal Agents as Smartphone Users
AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.
-
Beyond Logical Forms: LLM-Extracted Patterns for Fallacy Classification
LLM-extracted patterns merging logical structures and linguistic cues yield statistically significant gains in fallacy classification over zero-shot baselines with cross-dataset generalization.
-
MMoA: An AI-Agent framework with recurrence for Memoried Mixure-of-Agent
MMoA adds LSTM recurrence to Mixture-of-Agents routing, reaching 58.0% win rate on AlpacaEval 2.0 versus 59.8% for baseline MoA while cutting runtime by up to 4.6%.
-
Optimizing Abstractive Summarization With Fine-Tuned PEGASUS
Fine-tuned PEGASUS achieves state-of-the-art ROUGE scores on XL-Sum English corpus with 4.04% ROUGE-1, 15.25% ROUGE-2, and 3.39% ROUGE-L gains over mT5 baseline.