400 citations · 633 across the 18 of their papers we have counts for
18 papers
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
Song Wang, Zihan Chen, Peng Wang +5
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or special…
Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources
Alisia Lupidi, Carlos Gemmell, Nicola Cancedda +5
Synthetic data generation has recently emerged as a promising approach for enhancing the capabilities of large language models (LLMs) without the need for expensive human annotatio…
Self-Taught Evaluators
Tianlu Wang, Ilia Kulikov, Olga Golovneva +7
Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the s…
FairPair: A Robust Evaluation of Biases in Language Models through Paired Perturbations
Jane Dwivedi-Yu, Raaz Dwivedi, Timo Schick
The accurate evaluation of differential treatment in language models to specific groups is critical to ensuring a positive and safe user experience. An ideal evaluation should have…
TOOLVERIFIER: Generalization to New Tools via Self-Verification
Dheeraj Mekala, Jason Weston, Jack Lanchantin +4
Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learn…
Teaching Large Language Models to Reason with Reinforcement Learning
Alex Havrilla, Yuqing Du, Sharath Chandra Raparthy +6
Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we s…
MultiContrievers: Analysis of Dense Retrieval Representations
Seraphina Goldfarb-Tarrant, Pedro Rodriguez, Jane Dwivedi-Yu +1
Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affec…
GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
Alex Havrilla, Sharath Raparthy, Christoforus Nalmpantis +4
State-of-the-art language models can exhibit impressive reasoning refinement capabilities on math, science or coding tasks. However, recent work demonstrates that even the best mod…
Efficient Tool Use with Chain-of-Abstraction Reasoning
Silin Gao, Jane Dwivedi-Yu, Ping Yu +7
To achieve faithful reasoning that aligns with human expectations, large language models (LLMs) need to ground their reasoning to real-world knowledge (e.g., web facts, math and ph…
Evaluation of Faithfulness Using the Longest Supported Subsequence
Anirudh Mittal, Timo Schick, Mikel Artetxe +1
As increasingly sophisticated language models emerge, their trustworthiness becomes a pivotal issue, especially in tasks such as summarization and question-answering. Ensuring thei…
Shepherd: A Critic for Language Model Generation
Tianlu Wang, Ping Yu, Xiaoqing Ellen Tan +7
As large language models improve, there is increasing interest in techniques that leverage these models' capabilities to refine their own outputs. In this work, we introduce Shephe…
Active Learning Principles for In-Context Learning with Large Language Models
Katerina Margatina, Timo Schick, Nikolaos Aletras +1
The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examp…
Active Retrieval Augmented Generation
Zhengbao Jiang, Frank F. Xu, Luyu Gao +6
Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augme…
Augmented Language Models: a Survey
Grégoire Mialon, Roberto Dessì, Maria Lomeli +10
This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially comple…
Toolformer: Language Models Can Teach Themselves to Use Tools
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì +5
Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with…
EditEval: An Instruction-Based Benchmark for Text Improvements
Jane Dwivedi-Yu, Timo Schick, Zhengbao Jiang +6
Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterativ…
PEER: A Collaborative Language Model
Timo Schick, Jane Dwivedi-Yu, Zhengbao Jiang +7
Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process,…
Improving Wikipedia Verifiability with AI
Fabio Petroni, Samuel Broscheit, Aleksandra Piktus +10
Verifiability is a core content policy of Wikipedia: claims that are likely to be challenged need to be backed by citations. There are millions of articles available online and tho…