Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting their effectiveness as signals for shaping model behaviour.While individual factuality metrics are unreliable, their combination can more effectively capture diverse factual errors. We leverage this insight to introduce an automated training pipeline that improves factual consistency in summaries by aggregating scores from different weak metrics. Our approach avoids the need for complex reward shaping by mapping scores to preferences and filtering out cases with high disagreement between metrics. For each source document, we generate lexically similar summary pairs by varying decoding strategies, enabling the model to learn from factual differences caused by subtle lexical differences. This approach constructs a high-quality preference dataset using only source documents.Experiments demonstrate consistent factuality gains across models, ranging from early encoder-decoder architectures to modern large language models, with smaller models reaching comparable factuality to larger ones.

Learning from human feedback can improve models for text generation or passage ranking, aligning them better to a user’s needs. Data is often collected by asking users to compare alternative outputs to a given input, which may require a large number of comparisons to learn a ranking function. The amount of comparisons needed can be reduced using Bayesian Optimisation (BO) to query the user about only the most promising candidate outputs. Previous applications of BO to text ranking relied on shallow surrogate models to learn ranking functions over candidate outputs,and were therefore unable to fine-tune rankers based on deep, pretrained language models. This paper leverages Bayesian deep learning (BDL) to adapt pretrained language models to highly specialised text ranking tasks, using BO to tune the model with a small number of pairwise preferences between candidate outputs. We apply our approach to community question answering (cQA) and extractive multi-document summarisation (MDS) with simulated noisy users, finding that our BDL approach significantly outperforms both a shallow Gaussian process model and traditional active learning with a standard deep neural network, while remaining robust to noise in the user feedback.

Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data, time, storage, or energy, all of which are naturally limited and unevenly distributed. This motivates research into efficient methods that require fewer resources to achieve similar results. This survey synthesizes and relates current methods and findings in efficient NLP. We aim to provide both guidance for conducting NLP under limited resources, and point towards promising research directions for developing more efficient methods.

Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker’s persona. These models are trained with fully supervised learning where the objective function barely captures factual consistency. We propose to fine-tune these models by reinforcement learning and an efficient reward function that explicitly captures the consistency between a response and persona facts as well as semantic plausibility. Our automatic and human evaluations on the PersonaChat corpus confirm that our approach increases the rate of responses that are factually consistent with persona facts over its supervised counterpart while retains the language quality of responses.

The success of NLP research is founded on high-quality annotated datasets, which are usually obtained from multiple expert annotators or crowd workers. The standard practice to training machine learning models is to first adjudicate the disagreements and then perform the training. To this end, there has been a lot of work on aggregating annotations, particularly for classification tasks. However, many other tasks, particularly in NLP, have unique characteristics not considered by standard models of annotation, e.g., label interdependencies in sequence labelling tasks, unrestricted labels for anaphoric annotation, or preference labels for ranking texts. In recent years, researchers have picked up on this and are covering the gap. A first objective of this tutorial is to connect NLP researchers with state-of-the-art aggregation models for a diverse set of canonical language annotation tasks. There is also a growing body of recent work arguing that following the convention and training with adjudicated labels ignores any uncertainty the labellers had in their classifications, which results in models with poorer generalisation capabilities. Therefore, a second objective of this tutorial is to teach NLP workers how they can augment their (deep) neural models to learn from data with multiple interpretations.

Timeline Summarisation (TLS) aims to generate a concise, time-ordered list of events described in sources such as news articles. However, current systems do not provide an adequate way to adapt to new domains nor to focus on the aspects of interest to a particular user. Therefore, we propose a method for interactively learning abstractive TLS using Reinforcement Learning (RL). We define a compound reward function and use RL to fine-tune an abstractive Multi-document Summarisation (MDS) model, which avoids the need to train using reference summaries. One of the sub-reward functions will be learned interactively from user feedback to ensure the consistency between users’ demands and the generated timeline. The other sub-reward functions contribute to topical coherence and linguistic fluency. We plan experiments to evaluate whether our approach could generate accurate and precise timelines tailored for each user.

Disagreement between coders is ubiquitous in virtually all datasets annotated with human judgements in both natural language processing and computer vision. However, most supervised machine learning methods assume that a single preferred interpretation exists for each item, which is at best an idealization. The aim of the SemEval-2021 shared task on learning with disagreements (Le-Wi-Di) was to provide a unified testing framework for methods for learning from data containing multiple and possibly contradictory annotations covering the best-known datasets containing information about disagreements for interpreting language and classifying images. In this paper we describe the shared task and its results.

For many NLP applications, such as question answering and summarization, the goal is to select the best solution from a large space of candidates to meet a particular user’s needs. To address the lack of user or task-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. Unlike previous strategies, which attempt to learn a ranking across the whole candidate space, our method uses Bayesian optimization to focus the user’s labeling effort on high quality candidates and integrate prior knowledge to cope better with small data scenarios. We apply our method to community question answering (cQA) and extractive multidocument summarization, finding that it significantly outperforms existing interactive approaches. We also show that the ranking function learned by our method is an effective reward function for reinforcement learning, which improves the state of the art for interactive summarization.