相关论文: Interviewer-Candidate Role Play: Towards Developin…

Developing NLP models traditionally involves two stages - training and application. Retention of information acquired after training (at application time) is architecturally limited by the size of the model's context window (in the case of…

One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response…

Thanks to their scalability, two-stage recommenders are used by many of today's largest online platforms, including YouTube, LinkedIn, and Pinterest. These systems produce recommendations in two steps: (i) multiple nominators, tuned for low…

Response generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm of adapting such extremely large…

While large language models (LLMs) have significantly advanced mathematical reasoning, Process Reward Models (PRMs) have been developed to evaluate the logical validity of reasoning steps. However, PRMs still struggle with…

Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcomes, such as acquiring social-media contacts for private-channel conversion. Although…

Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are…

Natural language can offer a concise and human-interpretable means of specifying reinforcement learning (RL) tasks. The ability to extract rewards from a language instruction can enable the development of robotic systems that can learn from…

Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language…

Natural language processing (NLP) research combines the study of universal principles, through basic science, with applied science targeting specific use cases and settings. However, the process of exchange between basic NLP and…

Large Language Models (LLMs) have demonstrated impressive capabilities in generating coherent text but often struggle with grounding language and strategic dialogue. To address this gap, we focus on journalistic interviews, a domain rich in…

Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited…

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer,…

On-the-job learning consists in continuously learning while being used in production, in an open environment, meaning that the system has to deal on its own with situations and elements never seen before. The kind of systems that seem to be…

Recent studies have highlighted their proficiency in some simple tasks like writing and coding through various reasoning strategies. However, LLM agents still struggle with tasks that require comprehensive planning, a process that…

Organizations use asynchronous AI interview systems to efficiently manage large applicant pools, enabling quick and uniform evaluations. However, concerns remain about their impact on user agency and the lack of personalization applicants…

Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance due to their remarkable proficiency in various language-related tasks. However, LLMs are prone to generating factually incorrect…

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of…

Natural language processing (NLP) aims at investigating the interactions between agents and humans, processing and analyzing large amounts of natural language data. Large-scale language models play an important role in current natural…

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…