5 accepted papers
Existing attacks against multimodal language models often communicate instruction through text, either as an explicit malicious instruction or a crafted generic prompt, and accompanied by a toxic image. In contrast, here we exploit the capabilities of MLLMs in following non-textual instruction, i.e.…
Although LLM-based conversational agents demonstrate strong fluency and coherence, they still produce undesirable behaviors ( errors ) that are challenging to prevent from reaching users during deployment. Recent research leverages large language models (LLMs) to detect errors and guide response-gen
Scientific leaderboards are standardized ranking systems that facilitate evaluating and comparing competitive methods. Typically, a leaderboard is defined by a task, dataset, and evaluation metric (TDM) triple, allowing objective performance assessment and fostering innovation through benchmarking.…
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of such information on task completion and factual consistency, which are important c…
Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made on the prior distribution is incompatible with these distributions, thus restricting the diversity of generated respons…