Teaching language models to support answers with verified quotes

Menick, Jacob; Trebacz, Maja; Mikulik, Vladimir; Aslanides, John; Song, Francis; Chadwick, Martin J.; Glaese, Mia; Young, Susannah; Campbell-Gillingham, Lucy; Irving, Geoffrey; McAleese, Nat

doi:10.48550/arxiv.2203.11147

Cited by 18 publications

(20 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar approach could be derived for our setting. Enabling the model to support outputs with reference to particular locations within the visual inputs, or to external verified quotes is also interesting direction (Menick et al, 2022;Thoppilan et al, 2022). Finally, in Figure 11, we provide qualitative examples demonstrating that Flamingo can explain its own outputs, suggesting avenues to explainability and interpretability using the model's text interface.…”

Section: Risks and Mitigation Strategiesmentioning

confidence: 91%

Flamingo: a Visual Language Model for Few-Shot Learning

Alayrac¹,

Donahue²,

Luc³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

ordered alphabetically, † Equal contributions, ordered alphabetically, ‡ Equal senior contributions Building models that can be rapidly adapted to numerous tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. Flamingo models include key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of the proposed Flamingo models, exploring and measuring their ability to rapidly adapt to a variety of image and video understanding benchmarks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer, captioning tasks, which evaluate the ability to describe a scene or an event, and close-ended tasks such as multiple choice visual question-answering. For tasks lying anywhere on this spectrum, we demonstrate that a single Flamingo model can achieve a new state of the art for few-shot learning, simply by prompting the model with task-specific examples. On many of these benchmarks, Flamingo actually surpasses the performance of models that are fine-tuned on thousands of times more task-specific data.

show abstract

Section: Risks and Mitigation Strategiesmentioning

confidence: 91%

Flamingo: a Visual Language Model for Few-Shot Learning

Alayrac¹,

Donahue²,

Luc³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Rationales are typically defined as masks on the input passage (Lei et al, 2016), with the goal of finding the minimal rationale that is sufficient to identify the ground truth label (DeYoung et al, 2020). Such masks can be learned from human annotations (Zaidan et al, 2007;Menick et al, 2022) or from unsupervised objectives such as information bottleneck (Paranjape et al, 2020). We depart from fully extractive rationales by adding decontextualizing markup, unlike prior work in which decontextualization is performed inline (Choi et al, 2021), obscuring the relationship to the original text.…”

Section: Related Workmentioning

confidence: 99%

Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model

Eisenstein¹,

Andor²,

Bohnet³

et al. 2022

Preprint

View full text Add to dashboard Cite

Explainable question answering systems should produce not only accurate answers but also rationales that justify their reasoning and allow humans to check their work. But what sorts of rationales are useful and how can we train systems to produce them? We propose a new style of rationale for open-book question answering, called markup-and-mask, which combines aspects of extractive and free-text explanations. In the markup phase, the passage is augmented with free-text markup that enables each sentence to stand on its own outside the discourse context. In the masking phase, a sub-span of the marked-up passage is selected. To train a system to produce markup-and-mask rationales without annotations, we leverage in-context learning. Specifically, we generate silver annotated data by sending a series of prompts to a frozen pretrained language model, which acts as a teacher. We then fine-tune a smaller student model by training on the subset of rationales that led to correct answers. The student is "honest" in the sense that it is a pipeline: the rationale acts as a bottleneck between the passage and the answer, while the "untrusted" teacher operates under no such constraints. Thus, we offer a new way to build trustworthy pipeline systems from a combination of end-task annotations and frozen pretrained language models.

show abstract

“…1 and 2a), which contains all the information necessary to solve the problem, as well as potentially irrelevant distractors. In the future this assumption can be relaxed, for example by extracting the necessary information through search (Lazaridou et al, 2022;Menick et al, 2022). We also assume that all questions are well posed and definitively answerable given the context.…”

Section: The Selection-inference (Si) Frameworkmentioning

confidence: 99%

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Creswell¹,

Shanahan²,

Higgins³

2022

Preprint

View full text Add to dashboard Cite

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems.Here we carry out a comprehensive evaluation of LLMs on 50 tasks that probe different aspects of logical reasoning. We show that language models tend to perform fairly well at single step inference or entailment tasks, but struggle to chain together multiple reasoning steps to solve more complex problems. In light of this, we propose a Selection-Inference (SI) framework that exploits pre-trained LLMs as general processing modules, and alternates between selection and inference to generate a series of interpretable, casual reasoning steps leading to the final answer. We show that a 7B parameter LLM used within the SI framework in a 5-shot generalisation setting, with no fine-tuning, yields a performance improvement of over 100% compared to an equivalent vanilla baseline on a suite of 10 logical reasoning tasks. The same model in the same setting even outperforms a significantly larger 280B parameter baseline on the same suite of tasks. Moreover, answers produced by the SI framework are accompanied by a causal natural-language-based reasoning trace, which has important implications for the safety and trustworthiness of the system.

show abstract

Teaching language models to support answers with verified quotes

Cited by 18 publications

References 20 publications

Flamingo: a Visual Language Model for Few-Shot Learning

Flamingo: a Visual Language Model for Few-Shot Learning

Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Contact Info

Product

Resources

About