arXiv Machine Learning

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

arXiv AI
2d ago

The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier?

The paper presents a Pareto atlas of LLM inference optimizations, mapping cost, quality, and latency trade‑offs for Qwen2.5‑7B‑Instruct on L4, A100, and H100 GPUs. Using 54 measured configurations and a calibrated simulator, it identifies 18 of 36 setups on the Pareto frontier, showing that combined methods outperform single ones. Quality tests reveal that AWQ 4bit and FP8 weights offer significant latency reductions while largely preserving accuracy, but naive FP8 KV caching fails to answer any questions correctly.

By Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly
arXiv AI
Aug 11

Thought-Level Beam Search for Reasoning

arXiv:2608. 08020v1 Announce Type: new Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it.

By Lijie Yang, Hongyin Luo, Tri Dao, Ravi Netravali
arXiv AI
Aug 20

Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck

The paper examines test‑time scaling (TTS) methods that use extra inference compute to improve language model outputs. Across five open‑ended benchmarks—medicine, law, finance, general chat, and creative writing—the study finds that increasing exploration (generating more candidates) consistently yields better top candidates, but exploitation (selecting the final output) remains weak due to poor reward‑model correlation. Only the Fusion approach, which synthesizes candidates, reliably improves results, yet it recovers only about 40% of the potential quality, indicating that the bottleneck lies in choosing from the candidate pool rather than generating it.

By Davide Romano, Kanak Raj, Jerrod Parker, Daniele Giofr\`e
Hugging Face Trending Papers
Jul 28

How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost?

arXiv Machine Learning
Jul 24

Test-Time Scaling via Error Localization

arXiv:2607. 21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks.

By Rajiv Shailesh Chitale, Rahul Madhavan, Taneesh Gupta, Deepanway Ghosal, Aravindan Raghuveer
arXiv AI
Jul 29

How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

arXiv:2607. 25583v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore.

By Mahendra Singh Rathor, Anagheem Azzam
arXiv AI
Jul 24

Profiling Lightweight Large Language Models

arXiv:2607. 20806v1 Announce Type: new Abstract: Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resource-constrained edge and mobile environments.

By Tomohiro Harada, Enrique Alba, Gabriel Luque
arXiv Computation and Language
Aug 25

Can Large Language Models "Hyper-Thread"?

arXiv:2608.22376v1 Announce Type: new Abstract: Large language models generate tokens sequentially, but can they execute multiple tasks concurrently while forming each token? Broader attention alloca...

By Fei Ding