A panel of smaller diverse LLMs outperforms a single large model as an evaluator of generations, showing less intra-model bias and over 7x lower cost.
Transactions of the Association for Computational Linguistics 10 (Jan
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
Decisive combines document-grounded option scoring with adaptive Bayesian preference elicitation to achieve up to 20% higher decision accuracy than LLMs and existing frameworks across domains.
Introduces a parameter-driven framework for data attribution in LLMs that enables negotiation among creators, users, and intermediaries to meet stakeholder goals within the data economy.
The study filters non-English Wikipedia, reveals quality problems, proposes a 4-level ranking, and shows filtered data matches or beats raw data in language modeling with largest gains for lower-quality editions.
Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.
GPT-NeoX-20B is a publicly released 20B parameter autoregressive language model trained on the Pile that shows strong gains in five-shot reasoning over similarly sized prior models.
Analysis estimates 18.7% of Common Crawl documents contain geospatial information like coordinates and addresses, with little difference by language.
MMoA adds LSTM recurrence to Mixture-of-Agents routing, reaching 58.0% win rate on AlpacaEval 2.0 versus 59.8% for baseline MoA while cutting runtime by up to 4.6%.
citing papers explorer
-
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
GPT-NeoX-20B is a publicly released 20B parameter autoregressive language model trained on the Pile that shows strong gains in five-shot reasoning over similarly sized prior models.