We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to leverage their complementary strengths. One of the challenges of model fusion is high computational load, specifically in fine-tuning or aligning vocabularies. To address this, we propose Cool-Fusion, a simple yet effective approach that fuses the knowledge of source LLMs, which does not require training. Unlike ensemble methods, Cool-Fusion is applicable to any set of source LLMs that have different vocabularies. To overcome the vocabulary discrepancies among LLMs, we ensemble LLMs on text level, allowing them to rerank the generated texts by each other with different granularities. Extensive experiments have been conducted across a variety of benchmark datasets. On GSM8K, Cool-Fusion increases accuracy from three strong source LLMs by a significant margin of 17.4%.

Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and those presented in the LLMs’ training data. When dealing with complex problems, humans tend to think carefully before expressing solutions. However, they often do not articulate their inner thoughts, including their intentions and chosen methodologies. Consequently, critical insights essential for bridging reasoning steps may be absent in training data collected from human sources. To bridge this gap, we proposes inserting insights between consecutive reasoning steps, which review the status and initiate the next reasoning steps. Unlike prior prompting strategies that rely on a single or a workflow of static prompts to facilitate reasoning, insights are proactively generated to guide reasoning processes. We implement our idea as a reasoning framework, named Thinking Before You Speak (TBYS), and design a pipeline for automatically collecting and filtering in-context examples for the generation of insights, which alleviates human labeling efforts and fine-tuning overheads. Experiments on challenging mathematical datasets verify the effectiveness of TBYS. Project website: https://gitee.com/jswrt/TBYS

User Satisfaction Estimation (USE) is crucial in helping measure the quality of a task-oriented dialogue system. However, the complex nature of implicit responses poses challenges in detecting user satisfaction, and most datasets are limited in size or not available to the public due to user privacy policies. Unlike task-oriented dialogue, large-scale annotated chitchat with emotion labels is publicly available. Therefore, we present a novel user satisfaction model with domain adaptation (USMDA) to utilize this chitchat. We adopt a dialogue Transformer encoder to capture contextual features from the dialogue. And we reduce domain discrepancy to learn dialogue-related invariant features. Moreover, USMDA jointly learns satisfaction signals in the chitchat context with user satisfaction estimation, and user actions in task-oriented dialogue with dialogue action recognition. Experimental results on two benchmarks show that our proposed framework for the USE task outperforms existing unsupervised domain adaptation methods. To the best of our knowledge, this is the first work to study user satisfaction estimation with unsupervised domain adaptation from chitchat to task-oriented dialogue.

We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing attentive models exert attention on the sequential structure, we propose a way to incorporate attention into the tree topology. Specially, given a pair of sentences, our attentive encoder uses the representation of one sentence, which generated via an RNN, to guide the structural encoding of the other sentence on the dependency parse tree. We evaluate the proposed attentive encoder on three tasks: semantic similarity, paraphrase identification and true-false question selection. Experimental results show that our encoder outperforms all baselines and achieves state-of-the-art results on two tasks.