Leveraging external tools is a key feature for modern Language Models (LMs) to expand their capabilities and integrate them into existing systems. However, existing benchmarks primarily focus on the accuracy of tool calling—whether the correct tool is called with the correct parameters—and less on evaluating when LMs should (not) call tools. We develop a new benchmark, When2Call, which evaluates tool-calling decision-making: when to generate a tool call, when to ask follow-up questions and when to admit the question can’t be answered with the tools provided. We find that state-of-the-art tool-calling LMs show significant room for improvement on When2Call, indicating the importance of this benchmark. We also develop a training set for When2Call and leverage the multiple-choice nature of the benchmark to develop a preference optimization training regime, which shows considerably more improvement than traditional fine-tuning. We release the benchmark and training data as well as evaluation scripts.

Inferences from adjective-noun combinations like “Is artificial intelligence still intelligence?” provide a good test bed for LLMs’ understanding of meaning and compositional generalization capability, since there are many combinations which are novel to both humans and LLMs but nevertheless elicit convergent human judgments. We study a range of LLMs and find that the largest models we tested are able to draw human-like inferences when the inference is determined by context and can generalize to unseen adjective-noun combinations. We also propose three methods to evaluate LLMs on these inferences out of context, where there is a distribution of human-like answers rather than a single correct answer. We find that LLMs show a human-like distribution on at most 75% of our dataset, which is promising but still leaves room for improvement.

Extracting temporal relations between events and time expressions has many applications such as constructing event timelines and time-related question answering. It is a challenging problem which requires syntactic and semantic information at sentence or discourse levels, which may be captured by deep contextualized language models (LMs) such as BERT (Devlin et al., 2019). In this paper, we develop several variants of BERT-based temporal dependency parser, and show that BERT significantly improves temporal dependency parsing (Zhang and Xue, 2018a). We also present a detailed analysis on why deep contextualized neural LMs help and where they may fall short. Source code and resources are made available at https://github.com/bnmin/tdp_ranking.