Human evaluation of generated language through pairwise preference judgments is pervasive. However, under common scenarios, such as when generations from a model pair are very similar, or when stochastic decoding results in large variations in generations, it results in inconsistent preference ratings. We address these challenges by introducing a meta-evaluation measure, separability, which estimates how suitable a test instance is for pairwise preference evaluation. For a candidate test instance, separability samples multiple generations from a pair of models, and measures how distinguishable the two sets of generations are. Our experiments show that instances with high separability values yield more consistent preference ratings from both human- and auto-raters. Further, the distribution of separability allows insights into which test benchmarks are more valuable for comparing models. Finally, we incorporate separability into ELO ratings, accounting for how suitable each test instance might be for reliably ranking LLMs. Overall, separability has implications for consistent, efficient and robust preference evaluation of LLMs with both human- and auto-raters.

A hallmark of human intelligence is the ability to learn new concepts purely from language. Several recent approaches have explored training machine learning models via natural language supervision. However, these approaches fall short in leveraging linguistic quantifiers (such as ‘always’ or ‘rarely’) and mimicking humans in compositionally learning complex tasks. Here, we present LaSQuE, a method that can learn zero-shot classifiers from language explanations by using three new strategies - (1) modeling the semantics of linguistic quantifiers in explanations (including exploiting ordinal strength relationships, such as ‘always’ > ‘likely’), (2) aggregating information from multiple explanations using an attention-based mechanism, and (3) model training via curriculum learning. With these strategies, LaSQuE outperforms prior work, showing an absolute gain of up to 7% in generalizing to unseen real-world classification tasks.

Recent approaches have explored language- guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022). While these classifiers can generalize in zero-shot settings, their task performance often varies substantially between different language explanations in unpredictable ways (Lu et al., 2022; Gonen et al., 2022). Also, current approaches fail to leverage unlabeled examples that may be available in many scenarios. Here, we introduce TALC, a framework that uses data programming to adapt a language-guided classifier for a new task during inference when provided with explanations from multiple teachers and unlabeled test examples. Our results show that TALC consistently outperforms a competitive baseline from prior work by an impressive 9.3% (relative improvement). Further, we demonstrate the robustness of TALC to variations in the quality and quantity of provided explanations, highlighting its potential in scenarios where learning from multiple teachers or a crowd is involved. Our code is available at: https://github.com/WeiKangda/TALC.git.

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting the natural language explanation of a data point. This work proposes a novel AL architecture to support experts’ real-world need for label and explanation annotations in low-resource scenarios. Our AL architecture leverages an explanation-generation model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations. Automated and human evaluations demonstrate the effectiveness of incorporating explanations into AL sampling and the improved human annotation efficiency and trustworthiness with our AL architecture. Additional ablation studies illustrate the potential of our AL architecture for transfer learning, generalizability, and integration with large language models (LLMs). While LLMs exhibit exceptional explanation-generation capabilities for relatively simple tasks, their effectiveness in complex real-world tasks warrants further in-depth study.

Generalized quantifiers (e.g., few, most) are used to indicate the proportions predicates satisfy (for example, some apples are red). One way to interpret quantifier semantics is to explicitly bind these satisfactions with percentage scopes (e.g., 30%-40% of apples are red). This approach can be helpful for tasks like logic formalization and surface-form quantitative reasoning (Gordon and Schubert, 2010; Roy et al., 2015). However, it remains unclear if recent foundation models (Bommasani et al., 2021) possess this ability due to the absence of direct training signals. To explore this, we introduce QuRe, a crowd-sourced dataset of human-annotated generalized quantifiers in Wikipedia sentences featuring percentage-equipped predicates. We explore quantifier comprehension using PRESQUE, a framework that combines natural language inference and the Rational Speech Acts framework. Experimental results on the HVD dataset (Herbelot and Vecchi, 2015) and QuRe demonstrate PRESQUE’s superiority over a literal listener baseline, showing a 20% relative improvement in F1 in predicting percentage scopes for quantifiers, even with no additional training.

Human communication is a collaborative process. Speakers, on top of conveying their own intent, adjust the content and language expressions by taking the listeners into account, including their knowledge background, personalities, and physical capabilities. Towards building AI agents with similar abilities in language communication, we propose a novel rational reasoning framework, Pragmatic Rational Speaker (PRS), where the speaker attempts to learn the speaker-listener disparity and adjust the speech accordingly, by adding a light-weighted disparity adjustment layer into working memory on top of speaker’s long-term memory system. By fixing the long-term memory, the PRS only needs to update its working memory to learn and adapt to different types of listeners. To validate our framework, we create a dataset that simulates different types of speaker-listener disparities in the context of referential games. Our empirical results demonstrate that the PRS is able to shift its output towards the language that listeners are able to understand, significantly improve the collaborative task outcome, and learn the disparity more efficiently than joint training.

While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored. Here, we introduce a high-quality crowdsourced dataset of narratives for employing proverbs in context as a benchmark for abstract language understanding. The dataset provides fine-grained annotation of aligned spans between proverbs and narratives, and contains minimal lexical overlaps between narratives and proverbs, ensuring that models need to go beyond surface-level reasoning to succeed. We explore three tasks: (1) proverb recommendation and alignment prediction, (2) narrative generation for a given proverb and topic, and (3) identifying narratives with similar motifs. Our experiments show that neural language models struggle on these tasks compared to humans, and these tasks pose multiple learning challenges.

Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, a hallmark of human intelligence is the ability to learn new concepts purely from language. Here, we explore training zero-shot classifiers for structured data purely from language. For this, we introduce CLUES, a benchmark for Classifier Learning Using natural language ExplanationS, consisting of a range of classification tasks over structured data along with natural language supervision in the form of explanations. CLUES consists of 36 real-world and 144 synthetic classification tasks. It contains crowdsourced explanations describing real-world tasks from multiple teachers and programmatically generated explanations for the synthetic tasks. To model the influence of explanations in classifying an example, we develop ExEnt, an entailment-based model that learns classifiers using explanations. ExEnt generalizes up to 18% better (relative) on novel tasks than a baseline that does not use explanations. We delineate key challenges for automated learning from explanations, addressing which can lead to progress on CLUES in the future. Code and datasets are available at: https://clues-benchmark.github.io.

Transformer-based models have shown promising performance in numerous NLP tasks. However, recent work has shown the limitation of such models in showing compositional generalization, which requires models to generalize to novel compositions of known concepts. In this work, we explore two strategies for compositional generalization on the task of kinship prediction from stories, (1) data augmentation and (2) predicting and using intermediate structured representation (in form of kinship graphs). Our experiments show that data augmentation boosts generalization performance by around 20% on average relative to a baseline model from prior work not using these strategies. However, predicting and using intermediate kinship graphs leads to a deterioration in the generalization of kinship prediction by around 50% on average relative to models that only leverage data augmentation.

Existing approaches for the Table-to-Text task suffer from issues such as missing information, hallucination and repetition. Many approaches to this problem use Reinforcement Learning (RL), which maximizes a single manually defined reward, such as BLEU. In this work, we instead pose the Table-to-Text task as Inverse Reinforcement Learning (IRL) problem. We explore using multiple interpretable unsupervised reward components that are combined linearly to form a composite reward function. The composite reward function and the description generator are learned jointly. We find that IRL outperforms strong RL baselines marginally. We further study the generalization of learned IRL rewards in scenarios involving domain adaptation. Our experiments reveal significant challenges in using IRL for this task.

Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users. However, these techniques suffer from various sampling and association biases present in training data, often resulting in sub-par performance on content relevant to marginalized groups, potentially furthering disproportionate harms towards them. Studies on such biases so far have focused on only a handful of axes of disparities and subgroups that have annotations/lexicons available. Consequently, biases concerning non-Western contexts are largely ignored in the literature. In this paper, we introduce a weakly supervised method to robustly detect lexical biases in broader geo-cultural contexts. Through a case study on a publicly available toxicity detection model, we demonstrate that our method identifies salient groups of cross-geographic errors, and, in a follow up, demonstrate that these groupings reflect human judgments of offensive and inoffensive language in those geographic contexts. We also conduct analysis of a model trained on a dataset with ground truth labels to better understand these biases, and present preliminary mitigation experiments.

Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In this paper, we pose program generation from language as Inverse Reinforcement Learning. We introduce several interpretable reward components and jointly learn (1) a reward function that linearly combines them, and (2) a policy for program generation. Fine-tuning with our approach achieves significantly better performance than competitive methods using Reinforcement Learning (RL). On the VirtualHome framework, we get improvements of up to 9.0% on the Longest Common Subsequence metric and 14.7% on recall-based metrics over previous work on this framework (Puig et al., 2018). The approach is data-efficient, showing larger gains in performance in the low-data regime. Generated programs are also preferred by human evaluators over an RL-based approach, and rated higher on relevance, completeness, and human-likeness.

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair representations while maintaining performance on the target task. In this paper, we present an adversarial learning framework “Adversarial Scrubber” (AdS), to debias contextual representations. We perform theoretical analysis to show that our framework converges without leaking demographic information under certain conditions. We extend previous evaluation techniques by evaluating debiasing performance using Minimum Description Length (MDL) probing. Experimental evaluations on 8 datasets show that AdS generates representations with minimal information about demographic attributes while being maximally informative about the target task.

Recent work by Clark et al. (2020) shows that transformers can act as “soft theorem provers” by answering questions over explicitly provided knowledge in natural language. In our work, we take a step closer to emulating formal theorem provers, by proposing PRover, an interpretable transformer-based model that jointly answers binary questions over rule-bases and generates the corresponding proofs. Our model learns to predict nodes and edges corresponding to proof graphs in an efficient constrained training paradigm. During inference, a valid proof, satisfying a set of global constraints is generated. We conduct experiments on synthetic, hand-authored, and human-paraphrased rule-bases to show promising results for QA and proof generation, with strong generalization performance. First, PRover generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation). Second, when trained on questions requiring lower depths of reasoning, it generalizes significantly better to higher depths (up to 15% improvement). Third, PRover obtains near perfect QA accuracy of 98% using only 40% of the training data. However, generating proofs for questions requiring higher depths of reasoning becomes challenging, and the accuracy drops to 65% for “depth 5”, indicating significant scope for future work.

Multilingual individuals code switch between languages as a part of a complex communication process. However, most computational studies have examined only one or a handful of contextual factors predictive of switching. Here, we examine Naija-English code switching in a rich contextual environment to understand the social and topical factors eliciting a switch. We introduce a new corpus of 330K articles and accompanying 389K comments labeled for code switching behavior. In modeling whether a comment will switch, we show that topic-driven variation, tribal affiliation, emotional valence, and audience design all play complementary roles in behavior.

Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research effort in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generation of conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM can generate naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affect-discriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.