Copertina

BLEUBERI: BLEU is a surprisingly effective reward for instruction following

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chang, Yapei, Kim, Yekyung, Krumdick, Michael, Zadeh, Amir, Li, Chuan, Tanner, Chris, Iyyer, Mohit
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Argument Collapse: LLMs Flatten Long-Form Public Debate
di: Kim, Yekyung, et al.
Pubblicazione: (2026)

BooookScore: A systematic exploration of book-length summarization in the era of LLMs
di: Chang, Yapei, et al.
Pubblicazione: (2023)

PostMark: A Robust Blackbox Watermark for Large Language Models
di: Chang, Yapei, et al.
Pubblicazione: (2024)

BEARCUBS: A benchmark for computer-using web agents
di: Song, Yixiao, et al.
Pubblicazione: (2025)

FABLES: Evaluating faithfulness and content selection in book-length summarization
di: Kim, Yekyung, et al.
Pubblicazione: (2024)

SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation
di: Kim, Jung-Ho, et al.
Pubblicazione: (2024)

Enabling robots to follow abstract instructions and complete complex dynamic tasks
di: Mon-Williams, Ruaridh, et al.
Pubblicazione: (2024)

VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation
di: Song, Yixiao, et al.
Pubblicazione: (2024)

CaLMQA: Exploring culturally specific long-form question answering across 23 languages
di: Arora, Shane, et al.
Pubblicazione: (2024)

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
di: Liu, Shih-Yang, et al.
Pubblicazione: (2026)

How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs
di: Chang, Yapei, et al.
Pubblicazione: (2026)

Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
di: Samuel, Vinay, et al.
Pubblicazione: (2026)

One ruler to measure them all: Benchmarking multilingual long-context language models
di: Kim, Yekyung, et al.
Pubblicazione: (2025)

CLIPPER: Compression enables long-context synthetic data generation
di: Pham, Chau Minh, et al.
Pubblicazione: (2025)

People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
di: Russell, Jenna, et al.
Pubblicazione: (2025)

HelpSteer2: Open-source dataset for training top-performing reward models
di: Wang, Zhilin, et al.
Pubblicazione: (2024)

DocFinQA: A Long-Context Financial Reasoning Dataset
di: Reddy, Varshini, et al.
Pubblicazione: (2024)

Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
di: Bouchard, Dylan, et al.
Pubblicazione: (2025)

TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation
di: Filipek, Adam
Pubblicazione: (2025)

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
di: Dong, Guanting, et al.
Pubblicazione: (2024)

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings
di: Jiang, Yichen, et al.
Pubblicazione: (2024)

Revisiting the Superficial Alignment Hypothesis
di: Raghavendra, Mohit, et al.
Pubblicazione: (2024)

Non-instructional Fine-tuning: Enabling Instruction-Following Capabilities in Pre-trained Language Models without Instruction-Following Data
di: Xie, Juncheng, et al.
Pubblicazione: (2024)

ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment
di: Naous, Tarek, et al.
Pubblicazione: (2023)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
di: Patil, Vaidehi, et al.
Pubblicazione: (2025)

AI-University: An LLM-based platform for instructional alignment to scientific classrooms
di: Shojaei, Mostafa Faghih, et al.
Pubblicazione: (2025)

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
di: Lin, Han, et al.
Pubblicazione: (2025)

Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysis
di: Li, Junren, et al.
Pubblicazione: (2023)

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
di: Chen, Justin Chih-Yao, et al.
Pubblicazione: (2023)

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
di: Yadav, Prateek, et al.
Pubblicazione: (2023)

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
di: Hase, Peter, et al.
Pubblicazione: (2024)

VeriFastScore: Speeding up long-form factuality evaluation
di: Rajendhran, Rishanth, et al.
Pubblicazione: (2025)

Safety and accuracy follow different scaling laws in clinical large language models
di: Wind, Sebastian, et al.
Pubblicazione: (2026)

Soft Self-Consistency Improves Language Model Agents
di: Wang, Han, et al.
Pubblicazione: (2024)

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
di: Bouchard, Dylan, et al.
Pubblicazione: (2026)

Multi-Attribute Steering of Language Models via Targeted Intervention
di: Nguyen, Duy, et al.
Pubblicazione: (2025)

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
di: Khan, Zaid, et al.
Pubblicazione: (2024)

RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models
di: Huang, Jie, et al.
Pubblicazione: (2023)

Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
di: Bouchard, Dylan, et al.
Pubblicazione: (2026)

Effective Reasoning Chains Reduce Intrinsic Dimensionality
di: Prasad, Archiki, et al.
Pubblicazione: (2026)