7 papers · 1 filter
Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment
Haokai Zhao, Yunze Xiao, Weihao Xuan +3
Group alignment adapts a language model to a demographic group to produce responses that reflect the group's opinions, values, and preferences. Sycophancy, a well-documented by-pro…
CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning
Rahul Markasserithodi, Aditya Joshi, Yuekang Li +3
Despite advances in safety alignment, prompt-rewriting attacks such as persona modulation, fictional framing and persuasion-based reformulation, can bypass safety filters even on f…
A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
Bao Gia Doan, Aditya Joshi, Pantelis Elinas +4
RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Do…
Harnessing Test-time Adaptation for NLU tasks Involving Dialects of English
Duke Nguyen, Aditya Joshi, Flora Salim
Test-time domain adaptation (TTDA) is an excellent method which helps generalize models across domains, tasks, and distributions without the use of labeled datasets. Thus, TTDA is…
Alternatives To Next Token Prediction In Text Generation -- A Survey
Charlie Wyatt, Aditya Joshi, Flora Salim
The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as…
What am I missing here?: Evaluating Large Language Models for Masked Sentence Prediction
Charlie Wyatt, Aditya Joshi, Flora Salim
Transformer-based models primarily rely on Next Token Prediction (NTP), which predicts the next token in a sequence based on the preceding context. However, NTP's focus on single-t…