Instruction-tuned large language models (LLMs) excel at many tasks, and will even provide explanations for their behavior. Since these models are directly accessible to the public, there is a risk that convincing and wrong explanations can lead to unsupported confidence in LLMs. Therefore, interpretability-faithfulness of self-explanations is an important consideration for AI Safety. Assessing the interpretability-faithfulness of these explanations, termed self-explanations, is challenging as the models are too complex for humans to annotate what is a correct explanation. To address this, we propose employing self-consistency checks as a measure of faithfulness. For example, if an LLM says a set of words is important for making a prediction, then it should not be able to make the same prediction without these words. While self-consistency checks are a common approach to faithfulness, they have not previously been applied to LLM's self-explanations. We apply self-consistency checks to three types of self-explanations: counterfactuals, importance measures, and redactions. Our work demonstrate that faithfulness is both task and model dependent, e.g., for sentiment classification, counterfactual explanations are more faithful for Llama2, importance measures for Mistral, and redaction for Falcon 40B. Finally, our findings are robust to prompt-variations.

Many different fish species travel vast distances every year to reach their breeding grounds. Nowadays this journey is made more difficult due to obstacles such as water locks. One of these water locks placed along a popular route for migrating fish is the Weerdsluis in Utrecht. In order raise awareness, an initiative was launched together with the municipality of Utrecht: the Fish Doorbell. Here users could watch a livestream of the waters at the lock, and'ring' a bell if they spotted a fish.

Given one or two examples, humans are good at understanding how to solve a problem independently of its domain, because they are able to detect what the problem is and to choose the appropriate background knowledge according to the context. For instance, presented with the string "8/17/2017" to be transformed to "17th of August of 2017", humans will process this in two steps: (1) they recognise that it is a date and (2) they map the date to the 17th of August of 2017. Inductive Programming (IP) aims at learning declarative (functional or logic) programs from examples. Two key advantages of IP are the use of background knowledge and the ability to synthesise programs from a few input/output examples (as humans do). In this paper we propose to use IP as a means for automating repetitive data manipulation tasks, frequently presented during the process of {\em data wrangling} in many data manipulation problems. Here we show that with the use of general-purpose declarative (programming) languages jointly with generic IP systems and the definition of domain-specific knowledge, many specific data wrangling problems from different application domains can be automatically solved from very few examples. We also propose an integrated benchmark for data wrangling, which we share publicly for the community.

About a decade ago, spam brought email to near-ruin. The contest to save your inbox was on, with two of the world's biggest tech companies vying for the title of top spam-killer. By February 2012, Microsoft boasted that its spam filters were removing all but 3 percent of the junk messages from Hotmail, the company's online email service at the time. Google responded by claiming that its service, Gmail, removed all but about one percent of spam messages, adding that its false positives rate--legitimate mail misidentified as spam--was also about one percent. It was a point of pride for the two companies, particularly Microsoft, whose Hotmail service once carried such a poor reputation for spam. And the relative success of both showed that heuristic technologies--which identify spam based on a pre-defined rules--were working.