Large language models (LLMs) can solve complex multi-step problems, but
little is known about how these computations are implemented internally.
Motivated by this, we study how LLMs answer multi-hop queries such as "The
spouse of the performer of Imagine is". These queries require two information
extraction steps: a latent one for resolving the first hop ("the performer of
Imagine") into the bridge entity (John Lennon), and one for resolving the
second hop ("the spouse of John Lennon") into the target entity (Yoko Ono).
Understanding how the latent step is computed internally is key to
understanding the overall computation. By carefully analyzing the internal
computations of transformer-based LLMs, we discover that the bridge entity is
resolved in the early layers of the model. Then, only after this resolution,
the two-hop query is solved in the later layers. Because the second hop
commences in later layers, there could be cases where these layers no longer
encode the necessary knowledge for correctly predicting the answer. Motivated
by this, we propose a novel "back-patching" analysis method whereby a hidden
representation from a later layer is patched back to an earlier layer. We find
that in up to 57% of previously incorrect cases there exists a back-patch that
results in the correct generation of the answer, showing that the later layers
indeed sometimes lack the needed functionality. Overall our methods and
findings open further opportunities for understanding and improving latent
reasoning in transformer-based LLMs.

大型语言模型在解决复杂的多步问题方面能力强大，本研究通过分析 Transformer-based LLMs 内部计算过程，发现其在处理多跳查询和信息抽取时采用了潜在的计算步骤，进而提出了一种新颖的 “回补” 分析方法，帮助解决模型在后期计算中可能缺乏必要的功能，从而为理解和改进 Transformer-based LLMs 中的潜在推理提供更多机会。

滞后的跳跃：探索大型语言模型在多次跳跃查询上的限制

Hopping Too Late: Exploring the Limitations of Large Language Models on  Multi-Hop Queries

Retrieval-augmented generation (RAG) augments large language models (LLM) by
retrieving relevant knowledge, showing promising potential in mitigating LLM
hallucinations and enhancing response quality, thereby facilitating the great
adoption of LLMs in practice. However, we find that existing RAG systems are
inadequate in answering multi-hop queries, which require retrieving and
reasoning over multiple pieces of supporting evidence. Furthermore, to our
knowledge, no existing RAG benchmarking dataset focuses on multi-hop queries.
In this paper, we develop a novel dataset, MultiHop-RAG, which consists of a
knowledge base, a large collection of multi-hop queries, their ground-truth
answers, and the associated supporting evidence. We detail the procedure of
building the dataset, utilizing an English news article dataset as the
underlying RAG knowledge base. We demonstrate the benchmarking utility of
MultiHop-RAG in two experiments. The first experiment compares different
embedding models for retrieving evidence for multi-hop queries. In the second
experiment, we examine the capabilities of various state-of-the-art LLMs,
including GPT-4, PaLM, and Llama2-70B, in reasoning and answering multi-hop
queries given the evidence. Both experiments reveal that existing RAG methods
perform unsatisfactorily in retrieving and answering multi-hop queries. We hope
MultiHop-RAG will be a valuable resource for the community in developing
effective RAG systems, thereby facilitating greater adoption of LLMs in
practice. The MultiHop-RAG and implemented RAG system is publicly available at
this https URL

我们开发了一个新的数据集 MultiHop-RAG，它由知识库、大量的多跳查询、它们的真实答案和相应的支持证据组成，并详细介绍了构建数据集的过程。我们进行了两个实验来展示 MultiHop-RAG 的基准化效用，实验结果表明现有的 RAG 方法在检索和回答多跳查询上表现不尽人意。我们希望 MultiHop-RAG 能成为开发有效的 RAG 系统的有价值资源，从而促进 LLMs 在实践中的更广泛应用。