Fix authors for two 2024.kallm papers

data/xml/2024.kallm.xml

@@ -25,9 +25,9 @@
       <title>Multi-hop Database Reasoning with Virtual Knowledge Graph</title>
       <author><first>Juhee</first><last>Son</last></author>
       <author><first>Yeon</first><last>Seonwoo</last></author>
-      <author><first>Alice</first><last>Oh</last><affiliation>Korea Advanced Institute of Science and Technology</affiliation></author>
-      <author><first>James</first><last>Thorne</last><affiliation>KAIST</affiliation></author>
       <author><first>Seunghyun</first><last>Yoon</last><affiliation>Adobe Research</affiliation></author>
+      <author><first>James</first><last>Thorne</last><affiliation>KAIST</affiliation></author>
+      <author><first>Alice</first><last>Oh</last><affiliation>Korea Advanced Institute of Science and Technology</affiliation></author>
       <pages>1-11</pages>
       <abstract>Application of LLM to database queries on natural language sentences has demonstrated impressive results in both single and multi-hop scenarios.In the existing methodologies, the requirement to re-encode query vectors at each stage for processing multi-hop queries presents a significant bottleneck to the inference speed.This paper proposes VKGFR (Virtual Knowledge Graph based Fact Retriever) that leverages large language models to extract representations corresponding to a sentence’s knowledge graph, significantly enhancing inference speed for multi-hop reasoning without performance loss.Given that both the queries and natural language database sentences can be structured as a knowledge graph, we suggest extracting a Virtual Knowledge Graph (VKG) representation from sentences with LLM.Over the pre-constructed VKG, our VKGFR conducts retrieval with a tiny model structure, showing performance improvements with higher computational efficiency. We evaluate VKGFR on the WikiNLDB and MetaQA dataset, designed for multi-hop database reasoning over text. The results indicate 13x faster inference speed on the WikiNLDB dataset without performance loss.</abstract>
       <url hash="d9dd4e2f">2024.kallm-1.1</url>
@@ -147,11 +147,16 @@
     <paper id="13">
       <title>Improving <fixed-case>LLM</fixed-case>-based <fixed-case>KGQA</fixed-case> for multi-hop Question Answering with implicit reasoning in few-shot examples</title>
       <author><first>Mili</first><last>Shah</last><affiliation>Microsoft</affiliation></author>
-      <author><first>Jing</first><last>Tian</last></author>
+      <author><first>Joyce</first><last>Cahoon</last><affiliation>Microsoft</affiliation></author>
+      <author><first>Mirco</first><last>Milletari</last><affiliation>Microsoft</affiliation></author>
+      <author><first>Jing</first><last>Tian</last><affiliation>Microsoft</affiliation></author>
+      <author><first>Fotis</first><last>Psallidas</last><affiliation>Microsoft</affiliation></author>
+      <author><first>Andreas</first><last>Mueller</last><affiliation>Microsoft</affiliation></author>
+      <author><first>Nick</first><last>Litombe</last><affiliation>Microsoft</affiliation></author>
       <pages>125-135</pages>
       <abstract>Large language models (LLMs) have shown remarkable capabilities in generating natural language texts for various tasks. However, using LLMs for question answering on knowledge graphs still remains a challenge, especially for questions requiring multi-hop reasoning. In this paper, we present a novel planned query guidance approach that improves large language model (LLM) performance in multi-hop question answering on knowledge graphs (KGQA). We do this by designing few-shot examples that implicitly demonstrate a systematic reasoning methodology to answer multi-hop questions. We evaluate our approach for two graph query languages, Cypher and SPARQL, and show that the queries generated using our strategy outperform the queries generated using a baseline LLM and typical few-shot examples by up to 24.66% and 7.7% in execution match accuracy for the MetaQA and the Spider benchmarks respectively. We also conduct an ablation study to analyze the incremental effects of the different techniques of designing few-shot examples. Our results suggest that our approach enables the LLM to effectively leverage the few-shot examples to generate queries for multi-hop KGQA.</abstract>
       <url hash="9e621cf2">2024.kallm-1.13</url>
-      <bibkey>shah-tian-2024-improving</bibkey>
+      <bibkey>shah-etal-2024-improving</bibkey>
     </paper>
   </volume>
 </collection>