paper-with-me

Papers

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

2024-01-18 · Zdeněk Kasner, Ondřej Dušek

We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from structured data. To avoid the issue of LLM training data contamination with standard benchmarks, we design Quintd - a tool for collecting novel structured data records from public APIs. We find that open LLMs (Llama 2, Mistral, and Zephyr) can generate fluent and coherent texts in zero-shot settings from data in common formats collected with Quintd. However, we show that the semantic accuracy of the outputs is a major issue: both according to human annotators and our reference-free metric based on GPT-4, more than 80% of the outputs of open LLMs contain at least one semantic error. We publicly release the code, data, and model outputs.

📄 PDF Abstract BibTeX arXiv:2401.10186

Code (0)

등록된 구현이 없습니다.

Tasks

Data-to-Text GenerationIn-Context LearningText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Investigating naturalistic hand movements by behavior mining in long-term video and neural recordings

2020-01-23 · Satpreet H. Singh, Steven M. Peterson, Rajesh P. N. Rao, Bingni W. Brunton

Recent technological advances in brain recording and artificial intelligence are propelling a new paradigm in neuroscience beyond the traditional controlled experiment. Rather than focusing on cued, repeated trials, natu…

Experimental Design

On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe

2024-02-22 · Ningyu Xu, Qi Zhang, Menghan Zhang, Peng Qian 외

Probing and enhancing large language models' reasoning capacity remains a crucial open question. Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference. We use in-…

In-Context LearningReverse Dictionary

Simulating and analyzing a sparse order book: an application to intraday electricity markets

2024-10-09 · Philippe Bergault, Enzo Cognéville

This paper presents a novel model for simulating and analyzing sparse limit order books (LOBs), with a specific application to the European intraday electricity market. In illiquid markets, characterized by significant g…

Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems

2025-03-09 · Dany Moshkovich, Hadar Mulian, Sergey Zeltyn, Natti Eder 외

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle…

Benchmarking

Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics

2026-06-03 · Stella Biderman, Mohammad Aflah Khan, Niloofar Mireshghallah, Catherine Arnett 외 arxiv

What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures, and optimization dynamics. Yet much of …