5 accepted papers
Rubrics provide a flexible way to train LLMs on open-ended long-form answers where verifiable rewards are not applicable and human preferences provide coarse signals. Prior work shows that reinforcement learning with rubric-based rewards leads to consistent gains in LLM post-training. Most existing …
Human activity is moderated by norms; however, supervision for normative reasoning is sparse, particularly where norms are physically- or socially-grounded. We thus present EgoNormia \lVert 𝜖 \rVert, comprising 1,853 (200 for EgoNormia-verified) multiple choice questions (MCQs) grounded within ego-c…
Negation has been a long-standing challenge for language models.Previous studies have shown that they struggle with negation in many natural language understanding tasks.In this work, we propose a self-supervised method to make language models more robust against negation.We introduce a novel task,…
Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.…
Yes-no questions expect a yes or no for an answer, but people often skip polar keywords. Instead, they answer with long explanations that must be interpreted. In this paper, we focus on this challenging problem and release new benchmarks in eight languages. We present a distant supervision approach…