2.7k citations · 2.7k across the 19 of their papers we have counts for
13 papers · 1 filter
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Peng Du, Kiran Kamble, Rakshith Vasudev +5
Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Su…
Auditing LLM Benchmarks with Item Response Theory
Sander Land, Daniel M. Bikel
LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-based indicator that surfaces li…
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Zhenyu Zhao, Sander Land, Daniel M. Bikel +1
Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that r…
Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention
Rakshith Vasudev, Melisa Russak, Dan Bikel +1
Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic…
Post-training an LLM for RAG? Train on Self-Generated Demonstrations
Matthew Finlayson, Ilia Kulikov, Daniel M. Bikel +3
Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training m…
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
Yi-Lin Tuan, Xilun Chen, Eric Michael Smith +5
As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes s…
"Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing
Vipula Rawte, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman +4
Hallucination has emerged as the most vulnerable aspect of contemporary Large Language Models (LLMs). In this paper, we introduce the Sorry, Come Again (SCA) prompting, aimed to av…
When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
Norah Alzahrani, Hisham Abdullah Alyahya, Yazeed Alnumay +9
Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are take…
Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems
Hsuan Su, Rebecca Qian, Chinnadhurai Sankar +4
Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the…
Llama 2: Open Foundation and Fine-Tuned Chat Models
Hugo Touvron, Louis Martin, Kevin Stone +65
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our f…
Exploring Dual Encoder Architectures for Question Answering
Zhe Dong, Jianmo Ni, Daniel M. Bikel +4
Dual encoders have been used for question-answering (QA) and information retrieval (IR) tasks with good results. Previous research focuses on two major types of dual encoders, Siam…
Entity Linking via Dual and Cross-Attention Encoders
Oshin Agarwal, Daniel M. Bikel
Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and…
Large Scale Language Modeling in Automatic Speech Recognition
Ciprian Chelba, Dan Bikel, Maria Shugrina +2
Large language models have been proven quite beneficial for a variety of automatic speech recognition tasks in Google. We summarize results on Voice Search and a few YouTube speech…