Related papers: Testing SDRT's Right Frontier
Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks, spurring research into its underlying mechanisms. However, two primary challenges remain for real-world applications: (1) the…
Logic can define how agents are provided or denied access to resources, how to interlink resources using mining processes and provide users with choices for possible next steps in a workflow. These decisions are for the most part hidden,…
The Neural Contextual Reinforcement Framework introduces an innovative approach to enhancing the logical coherence and structural consistency of text generated by large language models. Leveraging reinforcement learning principles, the…
The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studies find models stubbornly retain their trained answers,…
Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control…
We present a preview of the Syntactic Acceptability Dataset, a resource being designed for both syntax and computational linguistics research. In its current form, the dataset comprises 1,000 English sequences from the syntactic discourse:…
Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…
A major challenge in structured prediction is to represent the interdependencies within output structures. When outputs are structured as sequences, linear-chain conditional random fields (CRFs) are a widely used model class which can learn…
Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…
Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of "Yes/No/Inquire" or generate a follow-up question when the decision is…
Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…
In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…
Aligning large language models with humans is challenging due to the inherently multifaceted nature of preference feedback. While existing approaches typically frame this as a multi-objective optimization problem, they often overlook how…
Regular transition systems (RTS) are a popular formalism for modeling infinite-state systems in general, and parameterised systems in particular. In a CONCUR 22 paper, Esparza et al. introduce a novel approach to the verification of RTS,…
In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned…
The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to objective adjudication. We demonstrate that this assumption is…
In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces that sound plausible…
Despite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet limited. In this…
Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label signal. We argue these gains are systematically misinterpreted: most reflect sharpening of…
Large language models (LLMs), owing to their extensive open-domain knowledge and semantic reasoning capabilities, have been increasingly integrated into recommender systems (RS). However, a substantial gap remains between the pre-training…