Papers with inference methods
Efficient Inference for Large Language Models –Algorithm, Model, and System (2025.emnlp-tutorials)
Copied to clipboard
| Challenge: | Inference of LLMs incurs high computational costs, memory access overhead, and memory usage, leading to inefficiencies in terms of latency, throughput, power consumption, and storage. |
| Approach: | This tutorial introduces the basics of efficient inference for LLMs and explains how to diagnose efficiency bottlenecks for a given workload on specific hardware. |
| Outcome: | The tutorial introduces the basic concepts of modern LLMs, software and hardware. |
Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling (2026.acl-srw)
Copied to clipboard
| Challenge: | Inference methods that prioritize raw performance over cost-effective compute usage are not efficient for real-world applications. |
| Approach: | They evaluate inference scaling strategies to determine their computational efficiency tradeoffs . they find debate and mixture-of-agents outperform self-consistency by 1.3% and 2.7% points . |
| Outcome: | The proposed scaling strategies outperform self-consistency, self-refinement, multi-agent debate and mixture-of-a agents on reasoning tasks. |
Quality-Aware Decoding for Neural Machine Translation (2022.naacl-main)
Copied to clipboard
Patrick Fernandes, António Farinhas, Ricardo Rei, José G. C. de Souza, Perez Ogayo, Graham Neubig, Andre Martins
| Challenge: | Despite advances in machine translation quality estimation and evaluation, decoding is mostly oblivious to this. |
| Approach: | They propose to use a decoding framework that is quality-aware for neural machine translation . they compare various methods like N-best reranking and minimum Bayes risk decoding . |
| Outcome: | The proposed quality-aware decoding outperforms MAP-based decoding on four datasets and two model classes. |
On Context Utilization in Summarization with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models excel in abstractive summarization tasks, delivering fluent and pertinent summaries. |
| Approach: | They conduct the first comprehensive study on context utilization and position bias in summarization. |
| Outcome: | The proposed benchmark compares two methods to alleviate position bias in summarization tasks. |
Recurrent Inference in Text Editing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing inference methods map the unedited text to the edited text or to the editing operations, but performance is degraded by the limited source text encoding and long, varying decoding steps. |
| Approach: | They propose a new inference method that iteratively performs editing actions . they introduce three types of editing tasks: AOR, AES, AEC . |
| Outcome: | The proposed method significantly narrows the problem space by iterating editing actions. |
Mapping the Course for Prompt-based Structured Prediction (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models have demonstrated strong performance in a wide-range of language tasks without task-specific fine-tuning. |
| Approach: | They combine large language models with combinatorial inference to marry predictive power of LLMs with structural consistency provided by inference methods. |
| Outcome: | The proposed model incorporates symbolic inference to provide consistent and accurate predictions on challenging tasks. |
Diffusion Language Model Inference with Monte Carlo Tree Search (2026.findings-eacl)
Copied to clipboard
Zheng Huang, Kiran Ramnath, Yueyan Chen, Aosong Feng, Sangmin Woo, Balasubramaniam Srinivasan, Zhichao Xu, Kang Zhou, Shuai Wang, Haibo Ding, Lin Lee Cheong
| Challenge: | Existing methods for inference use heuristics to determine which positions to unmask and which tokens to commit . MEDAL is an inference-time scaling framework that integrates Monte Carlo Tree SEarch initialization for Diffusion Language Model inference. |
| Approach: | They propose a framework that integrates Monte Carlo Tree SEarch initialization for Diffusion Language Model inference. |
| Outcome: | The proposed framework achieves 22.0% improvement over existing inference strategies across multiple benchmarks. |
TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs (2026.findings-eacl)
Copied to clipboard
Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee
| Challenge: | Large Vision Language Models (LVLMs) are advanced models that process multiple modalities, such as images, audio, and video, alongside text. |
| Approach: | They propose to use a method to generate and verify draft tokens in parallel . they compare existing methods with small draft models and observe performance fluctuations . |
| Outcome: | The proposed method achieves an average walltime speedup of 1.74 over autoregressive decoding and a 5% improvement over single drafting methods. |
Debiasing Multimodal Models via Causal Information Minimization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for debiasing multimodal models use approximate heuristics to represent the biases, such as shallow features from early stages of training or unimodal features for multimodal tasks like VQA, which may not be accurate. |
| Approach: | They propose a method that leverages causally-motivated information minimization to learn the confounder representations of a causal graph for multimodal data. |
| Outcome: | The proposed method improves out-of-distribution performance on multiple multimodal datasets without sacrificing in-distance performance. |
Unlocking the Potential of Diffusion Language Models through Template Infilling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on prefix-based prompting, resulting in a lack of stability and a large computational time. |
| Approach: | They propose a conditioning methodology tailored for Diffusion Language Models that distributes structural anchors across the target response, establishing a global template before infilling masked segments. |
| Outcome: | The proposed method improves on mathematical reasoning, code generation, and trip planning benchmarks while maintaining speed and robustness. |
Benchmarking Approximate Inference Methods for Neural Structured Prediction (N19-1)
Copied to clipboard
| Challenge: | Structured prediction models often involve complex inference problems for which finding exact solutions is intractable. |
| Approach: | They propose to perform gradient descent with respect to the output structure directly and train a neural network to perform inference. |
| Outcome: | The proposed methods achieve better speed/accuracy/search error trade-off than gradient descent while being faster than exact inference at similar accuracy levels. |
Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models demonstrate remarkable ability for learning to solve new tasks from a few examples. |
| Approach: | They propose to use templates to aggregate model predictions across multiple templates to improve model performance. |
| Outcome: | The proposed model ensembles boost model predictions while being robust to the choice of random set of templates. |
Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that MBR decoding improves model generation performance . however, the theoretical underpinnings of these results remain uncertain . |
| Approach: | They propose a theoretical interpretation of MBR decoding from the perspective of bias–diversity decomposition. |
| Outcome: | The proposed method improves the quality estimation of hypotheses by decomposing bias and diversity into two main factors. |