Related papers: OnePred: Next-Query Prediction via Recursive Inten…
Recent dialogue approaches operate by reading each word in a conversation history, and aggregating accrued dialogue information into a single state. This fixed-size vector is not expandable and must maintain a consistent format over time.…
The proliferation of large language models (LLMs) with varying computational costs and performance profiles presents a critical challenge for scalable, cost-effective deployment in real-world applications. We introduce a unified routing…
Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…
The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the inadequacy of…
Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models…
Effective persuasive dialogue agents adapt their strategies to individual users, accounting for the evolution of their psychological states and intentions throughout conversations. We present a personality-aware reinforcement learning…
In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…
Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making,…
A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…
Query Processing (QP) bridges user intent and content supply in large-scale Social Network Service (SNS) search engines. Traditional QP systems rely on pipelines of isolated discriminative models (e.g., BERT), suffering from limited…
In recent years, large language models (LLMs) have excelled in language understanding and generation, powering advanced dialogue and recommendation systems. However, a significant limitation persists: these systems often model user…
Identifying user preferences in dialogue systems is a pivotal aspect of providing satisfying services. Current research shows that using large language models (LLMs) to fine-tune a task-specific preference extractor yields excellent results…
In recent years, world business in online discussions and opinion sharing on social media is booming. Re-entry prediction task is thus proposed to help people keep track of the discussions which they wish to continue. Nevertheless, existing…
Large language model (LLM)-based multi-agent systems have shown strong potential for complex reasoning by coordinating specialized agents through structured communication. However, existing topology-evolution methods typically construct or…
Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of attention-based models is bottle-necked during inference by the…
Despite recent advances in understanding and leveraging long-range conversational memory, existing benchmarks still lack systematic evaluation of large language models(LLMs) across diverse memory dimensions, particularly in multi-session…
Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort. In this work, we introduce this pondering process into language models by repeatedly invoking the forward process…
In reasoning about sequential events it is natural to pose probabilistic queries such as "when will event A occur next" or "what is the probability of A occurring before B", with applications in areas such as user modeling, medicine, and…
Revolutionary advancements in Large Language Models have drastically reshaped our interactions with artificial intelligence systems. Despite this, a notable hindrance remains-the deficiency of a long-term memory mechanism within these…