MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods fall short.
CoRR, abs/1903.05566
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
We have recently seen the emergence of several publicly available Natural Language Understanding (NLU) toolkits, which map user utterances to structured, but more abstract, Dialogue Act (DA) or Intent specifications, while making this process accessible to the lay developer. In this paper, we present the first wide coverage evaluation and comparison of some of the most popular NLU services, on a large, multi-domain (21 domains) dataset of 25K user utterances that we have collected and annotated with Intent and Entity Type specifications and which will be released as part of this submission. The results show that on Intent classification Watson significantly outperforms the other platforms, namely, Dialogflow, LUIS and Rasa; though these also perform well. Interestingly, on Entity Type recognition, Watson performs significantly worse due to its low Precision. Again, Dialogflow, LUIS and Rasa perform well on this task.
fields
cs.CL 3verdicts
UNVERDICTED 3representative citing papers
TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.
FIAD is a new resource that encodes three Korean utterance patterns from banking reviews into Local Grammar Graphs to generate diverse annotated NLU training data, producing strong intent and topic extraction results on DIET-based models.
citing papers explorer
-
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods fall short.
-
Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings
TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.
-
Building Korean linguistic resource for NLU data generation of banking app CS dialog system
FIAD is a new resource that encodes three Korean utterance patterns from banking reviews into Local Grammar Graphs to generate diverse annotated NLU training data, producing strong intent and topic extraction results on DIET-based models.