Image de couverture de livre

How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chang, Yapei, Lo, Kyle, Iyyer, Mohit, Soldaini, Luca
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

BooookScore: A systematic exploration of book-length summarization in the era of LLMs
par: Chang, Yapei, et autres
Publié: (2023)

PostMark: A Robust Blackbox Watermark for Large Language Models
par: Chang, Yapei, et autres
Publié: (2024)

Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
par: Samuel, Vinay, et autres
Publié: (2026)

BEARCUBS: A benchmark for computer-using web agents
par: Song, Yixiao, et autres
Publié: (2025)

BLEUBERI: BLEU is a surprisingly effective reward for instruction following
par: Chang, Yapei, et autres
Publié: (2025)

Argument Collapse: LLMs Flatten Long-Form Public Debate
par: Kim, Yekyung, et autres
Publié: (2026)

CLIPPER: Compression enables long-context synthetic data generation
par: Pham, Chau Minh, et autres
Publié: (2025)

FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
par: Weller, Orion, et autres
Publié: (2024)

FABLES: Evaluating faithfulness and content selection in book-length summarization
par: Kim, Yekyung, et autres
Publié: (2024)

OverThink: Slowdown Attacks on Reasoning LLMs
par: Kumar, Abhinav, et autres
Publié: (2025)

Olmix: A Framework for Data Mixing Throughout LM Development
par: Chen, Mayee F., et autres
Publié: (2026)

olmOCR 2: Unit Test Rewards for Document OCR
par: Poznanski, Jake, et autres
Publié: (2025)

How Far Can Fairness Constraints Help Recover From Biased Data?
par: Sharma, Mohit, et autres
Publié: (2023)

DataDecide: How to Predict Best Pretraining Data with Small Experiments
par: Magnusson, Ian, et autres
Publié: (2025)

Evaluating LLMs' Reasoning Over Ordered Procedural Steps
par: Anika, Adrita, et autres
Publié: (2025)

How Random is Random? Evaluating the Randomness and Humaness of LLMs' Coin Flips
par: Van Koevering, Katherine, et autres
Publié: (2024)

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
par: Zhang, Jie, et autres
Publié: (2024)

Paloma: A Benchmark for Evaluating Language Model Fit
par: Magnusson, Ian, et autres
Publié: (2023)

CaLMQA: Exploring culturally specific long-form question answering across 23 languages
par: Arora, Shane, et autres
Publié: (2024)

Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries
par: Malaviya, Chaitanya, et autres
Publié: (2024)

Teaching Models to Understand (but not Generate) High-risk Data
par: Wang, Ryan, et autres
Publié: (2025)

How Vulnerable Are Edge LLMs?
par: Ding, Ao, et autres
Publié: (2026)

How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
par: Ambrogioni, Luca
Publié: (2026)

Improving Reinforcement Learning Sample-Efficiency using Local Approximation
par: Prashant, Mohit, et autres
Publié: (2025)

Towards Cross-Table Masked Pretraining for Web Data Mining
par: Ye, Chao, et autres
Publié: (2023)

Exploring How LLMs Capture and Represent Domain-Specific Knowledge
par: Garcia, Mirian Hipolito, et autres
Publié: (2025)

How can representation dimension dominate structurally pruned LLMs?
par: Xu, Mingxue, et autres
Publié: (2025)

How do Machine Learning Models Change?
par: Castaño, Joel, et autres
Publié: (2024)

MillStone: How Open-Minded Are LLMs?
par: Triedman, Harold, et autres
Publié: (2025)

Why LLMs Cannot Think and How to Fix It
par: Jahrens, Marius, et autres
Publié: (2025)

How Good Are LLMs at Processing Tool Outputs?
par: Kate, Kiran, et autres
Publié: (2025)

How Does Quantization Affect Multilingual LLMs?
par: Marchisio, Kelly, et autres
Publié: (2024)

How Neural Losses Shape VAE Latents
par: Strano, Giorgio, et autres
Publié: (2026)

How to Train Your LLM Web Agent: A Statistical Diagnosis
par: Vattikonda, Dheeraj, et autres
Publié: (2025)

Self-Directed Synthetic Dialogues and Revisions Technical Report
par: Lambert, Nathan, et autres
Publié: (2024)

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
par: Favero, Alessandro, et autres
Publié: (2025)

How Susceptible are LLMs to Influence in Prompts?
par: Anagnostidis, Sotiris, et autres
Publié: (2024)

How to Train Data-Efficient LLMs
par: Sachdeva, Noveen, et autres
Publié: (2024)

Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?
par: Li, Xiang, et autres
Publié: (2025)

Retrieval-Augmented Mining of Temporal Logic Specifications from Data
par: Saveri, Gaia, et autres
Publié: (2024)