arXiv AI
Jun 26
The Capability Frontier: Benchmarks Miss 82% of Model Performance
arXiv:2606. 26836v1 Announce Type: new Abstract: Existing benchmarks typically report accuracy for a single model on a single run.
Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks
arXiv:2607. 09739v1 Announce Type: new Abstract: We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite.
Related stories
arXiv AI
Sep 21
Balance of Benchmarks: Semantic Density Reweighting for Task-Conditioned Model Comparison
The paper introduces Balance of Benchmarks (BoB), a framework that improves task-conditioned model comparison by weighting benchmark evidence based on semantic density, equating scores across varying difficulty levels, and pooling task-relevant residuals. BoB retains all eligible benchmark data while adjusting its influence, outperforming uniform averaging on the WildScores dataset with higher Spearman correlation, lower MAE, and better shortlist hit rates. The method also reduces ranking instability when benchmarks are repeated or paraphrased, and lowers retrospective regret in model selection.
arXiv AI
Jun 2
Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs
arXiv:2606. 01400v1 Announce Type: cross Abstract: Evaluating large language models (LLMs) across comprehensive benchmarks is expensive and time-consuming.
arXiv AI
Jun 30
Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation
arXiv:2606. 29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding.
arXiv Machine Learning
Jun 19
A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)
arXiv:2602. 14696v2 Announce Type: replace Abstract: Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task.
arXiv Computation and Language
Sep 14
Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models
arXiv:2609.12475v1 Announce Type: new Abstract: Comprehensive benchmark suites are essential for improving large language models (LLMs), but many widely used benchmarks are redundant, making evaluati...
arXiv Machine Learning
Jun 29
Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings
arXiv:2606. 27997v1 Announce Type: new Abstract: Benchmarks of machine learning models often include many datasets, making evaluation expensive.
arXiv Computation and Language
4d ago
MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment
arXiv:2609.37574v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can...
arXiv AI
Sep 1
Balance of Benchmarks: Semantic Density Reweighting for Benchmark Multiplicity and Task-Conditioned Evaluation
arXiv:2608.30044v1 Announce Type: new Abstract: Language models are commonly compared by averaging scores across a benchmark list with equal weight. Such lists grow through publication outside an exp...
arXiv Machine Learning
Jul 20
VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs
arXiv:2607. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.
arXiv Computation and Language
6d ago
Large Language Model Selection with Limited Annotations
arXiv:2605.24981v2 Announce Type: replace Abstract: Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotati...
Hugging Face Trending Papers
Aug 19
Pairwise Ranking Outperforms Single-Action RL for Offline Explanation Selection: A Practical Lesson
The paper presents a cost‑effective approach for industrial explainable‑recommendation systems by decoupling explanation generation from selection. Explanations are pre‑generated using six prompt styles and two commodity LLMs, then a lightweight CPU‑resident selector (e.g., LambdaRank) chooses the best one at request time, achieving sub‑100 ms latency without GPUs. Experiments on a 2,958‑pair Google Local subset and a 300‑pair MovieLens‑1M split show that pairwise ranking outperforms single‑action RL methods, while KG‑path selectors achieve near‑perfect unique‑output rates, and the overall end‑to‑end build cost is around $15 on commodity hardware.