DGAO uses reinforcement learning to optimize LLMs for both accuracy and order stability by balancing intra-group accuracy advantages and inter-group stability advantages.
hub
Proceedings of the 2013 conference on empirical methods in natural language processing , pages=
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
representative citing papers
Synthetic data augmentation helps channel-mixing time series models but degrades channel-independent ones, with reliable gains only from seasonal-trend generators and gradual schedules in low-resource settings.
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
Prompt tuning matches full model tuning performance on large language models while tuning only a small fraction of parameters and improves robustness to domain shifts.
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
NASH decomposes the validation utility into Shapley-informative component functions and aggregates them non-linearly to make Data Shapley-based data selection consistently effective.
AdaLeZO uses a non-stationary multi-armed bandit to adaptively allocate perturbation budget across layers in zeroth-order optimization and applies inverse probability weighting to reduce variance while preserving unbiased gradients, delivering 1.7x-3.0x wall-clock speedup on LLaMA and OPT models.
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.
Combines POS filtering and perplexity loss to generate sensible universal adversarial triggers that drop SST sentiment accuracy to 0.04-0.12, with adversarial training raising it to 0.48.
Auto-CoT automatically generates and filters reasoning-enhanced demonstrations to improve in-context learning accuracy on complex reasoning tasks.
ClaHF converts instance labels into preference signals via candidate predictions and a reward model, then applies RL optimization to improve text classification accuracy and calibration.
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.
citing papers explorer
-
Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization
DGAO uses reinforcement learning to optimize LLMs for both accuracy and order stability by balancing intra-group accuracy advantages and inter-group stability advantages.
-
Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
Synthetic data augmentation helps channel-mixing time series models but degrades channel-independent ones, with reliable gains only from seasonal-trend generators and gradual schedules in low-resource settings.
-
A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
-
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
-
The Power of Scale for Parameter-Efficient Prompt Tuning
Prompt tuning matches full model tuning performance on large language models while tuning only a small fraction of parameters and improves robustness to domain shifts.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
Is Data Shapley Not Better than Random in Data Selection? Ask NASH
NASH decomposes the validation utility into Shapley-informative component functions and aggregates them non-linearly to make Data Shapley-based data selection consistently effective.
-
Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
AdaLeZO uses a non-stationary multi-armed bandit to adaptively allocate perturbation budget across layers in zeroth-order optimization and applies inverse probability weighting to reduce variance while preserving unbiased gradients, delivering 1.7x-3.0x wall-clock speedup on LLaMA and OPT models.
-
TLoRA: Task-aware Low Rank Adaptation of Large Language Models
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
-
The Falcon Series of Open Language Models
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
-
REPLUG: Retrieval-Augmented Black-Box Language Models
REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.
-
Universal Adversarial Triggers
Combines POS filtering and perplexity loss to generate sensible universal adversarial triggers that drop SST sentiment accuracy to 0.04-0.12, with adversarial training raising it to 0.48.
-
ACIL: Auto Chain of Thoughts for In-Context Learning
Auto-CoT automatically generates and filters reasoning-enhanced demonstrations to improve in-context learning accuracy on complex reasoning tasks.
-
ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks
ClaHF converts instance labels into preference signals via candidate predictions and a reward model, then applies RL optimization to improve text classification accuracy and calibration.
-
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.