To comprehensively gauge the capacity of current models for complex reasoning, it is crucial to assess their step-by-step reasoning in a scalable manner. Established reference-based evaluation metrics rely on human-annotated reasoning chains as references to assess the model-derived chains. However, such “gold-standard” human-written reasoning chains may not be unique and their acquisition is often labor-intensive. Existing reference-free reasoning evaluation metrics, while eliminating the need for human-crafted reasoning chains as references, often require fine-tuning with human-derived chains before evaluation, complicating the process and questioning their adaptability to other datasets. To address these challenges, we harness GPT-4 to automatically evaluate reasoning chain quality, thereby removing the dependency on human-written reasoning chains for both model fine-tuning and evaluative purposes. Leveraging the Socratic method, we develop SocREval (**Soc**ratic Method-Inspired **R**easoning **Eval**uation), a novel approach for prompt design in reference-free reasoning evaluation. Empirical results from four human annotated datasets reveal that SocREval significantly improves GPT-4’s performance, surpassing existing reference-free and reference-based reasoning evaluation metrics. Beyond its demonstrated efficacy, SocREval, proves to be both cost-efficient and robust to prompt writing and example selection, as substantiated by our in-depth analysis.

In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. We discover that LLM’s performance exceeds humans and surpasses the performance of state-of-the-art methods fine-tuned on extensive datasets. We additionally explore and analyze biases present in LLMs, including positional bias, lexical bias, order bias, which may affect their evaluative judgments. Our findings reveal a consistent bias in both GPT-3.5 and GPT-4 towards the second candidate response presented, attributed to prompt design. We also uncover a lexical bias in both GPT-3.5 and GPT-4, especially when label sets carry connotations such as numerical or sequential, highlighting the critical need for careful label verbalizer selection in prompt design. Additionally, our analysis indicates a tendency of both models to favor the debate’s concluding side as the winner, suggesting an end-of-discussion bias.

Unraveling the intricate details of events in natural language necessitates a subtle understanding of temporal dynamics. Despite the adeptness of Large Language Models (LLMs) in discerning patterns and relationships from data, their inherent comprehension of temporal dynamics remains a formidable challenge. This research meticulously explores these intrinsic challenges within LLMs, with a specific emphasis on evaluating the performance of GPT-3.5 and GPT-4 models in the analysis of temporal data. Employing two distinct prompt types, namely Question Answering (QA) format and Textual Entailment (TE) format, our analysis probes into both implicit and explicit events. The findings underscore noteworthy trends, revealing disparities in the performance of GPT-3.5 and GPT-4. Notably, biases toward specific temporal relationships come to light, with GPT-3.5 demonstrating a preference for “AFTER” in the QA format for both implicit and explicit events, while GPT-4 leans towards “BEFORE”. Furthermore, a consistent pattern surfaces wherein GPT-3.5 tends towards “TRUE”, and GPT-4 exhibits a preference for “FALSE” in the TE format for both implicit and explicit events. This persistent discrepancy between GPT-3.5 and GPT-4 in handling temporal data highlights the intricate nature of inductive bias in LLMs, suggesting that the evolution of these models may not merely mitigate bias but may introduce new layers of complexity.

Real-world applications often require improved models by leveraging *a range of cheap incidental supervision signals*. These could include partial labels, noisy labels, knowledge-based constraints, and cross-domain or cross-task annotations – all having statistical associations with gold annotations but not exactly the same. However, we currently lack a principled way to measure the benefits of these signals to a given target task, and the common practice of evaluating these benefits is through exhaustive experiments with various models and hyperparameters. This paper studies whether we can, *in a single framework, quantify the benefits of various types of incidental signals for a given target task without going through combinatorial experiments*. We propose a unified PAC-Bayesian motivated informativeness measure, PABI, that characterizes the uncertainty reduction provided by incidental supervision signals. We demonstrate PABI’s effectiveness by quantifying the value added by various types of incidental signals to sequence tagging tasks. Experiments on named entity recognition (NER) and question answering (QA) show that PABI’s predictions correlate well with learning performance, providing a promising way to determine, ahead of learning, which supervision signals would be beneficial.

Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, can we use QAMR (Michael et al., 2017) to improve named entity recognition? We suggest that simply further pre-training BERT is often not the best option, and propose the question-answer driven sentence encoding (QuASE) framework. QuASE learns representations from QA data, using BERT or other state-of-the-art contextual language models. In particular, we observe the need to distinguish between two types of sentence encodings, depending on whether the target task is a single- or multi-sentence input; in both cases, the resulting encoding is shown to be an easy-to-use plugin for many downstream tasks. This work may point out an alternative way to supervise NLP tasks.

We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.

Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general. Spatial relations between objects can either be explicit – expressed as spatial prepositions, or implicit – expressed by spatial verbs such as moving, walking, shifting, etc. Both these, but implicit relations in particular, require significant common sense understanding. In this paper, we introduce the task of inferring implicit and explicit spatial relations between two entities in an image. We design a model that uses both textual and visual information to predict the spatial relations, making use of both positional and size information of objects and image embeddings. We contrast our spatial model with powerful language models and show how our modeling complements the power of these, improving prediction accuracy and coverage and facilitates dealing with unseen subjects, objects and relations.

For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low quality and could hurt the learning process. This paper questions this common perception, motivated by the fact that structures consist of interdependent sets of variables. Thus, given a fixed budget, partly annotating each structure may provide the same level of supervision, while allowing for more structures to be annotated. We provide an information theoretic formulation for this perspective and use it, in the context of three diverse structured learning tasks, to show that learning from partial structures can sometimes outperform learning from complete ones. Our findings may provide important insights into structured data annotation schemes and could support progress in learning protocols for structured tasks.

Several corpora have been annotated with negation scope—the set of words whose meaning is negated by a cue like the word “not”—leading to the development of classifiers that detect negation scope with high accuracy. We show that for nearly all of these corpora, this high accuracy can be attributed to a single fact: they frequently annotate negation scope as a single span of text delimited by punctuation. For negation scopes not of this form, detection accuracy is low and under-sampling the easy training examples does not substantially improve accuracy. We demonstrate that this is partly an artifact of annotation guidelines, and we argue that future negation scope annotation efforts should focus on these more difficult cases.

We focus on named entity recognition (NER) for Chinese social media. With massive unlabeled text and quite limited labelled corpus, we propose a semi-supervised learning model based on B-LSTM neural network. To take advantage of traditional methods in NER such as CRF, we combine transition probability with deep learning in our model. To bridge the gap between label accuracy and F-score of NER, we construct a model which can be directly trained on F-score. When considering the instability of F-score driven method and meaningful information provided by label accuracy, we propose an integrated method to train on both F-score and label accuracy. Our integrated model yields 7.44% improvement over previous state-of-the-art result.

Negation cue detection involves identifying the span inherently expressing negation in a negative sentence. In Chinese, negative cue detection is complicated by morphological proprieties of the language. Previous work has shown that negative cue detection in Chinese can benefit from specific lexical and morphemic features, as well as cross-lingual information. We show here that they are not necessary: A bi-directional LSTM can perform equally well, with minimal feature engineering. In particular, the use of a character-based model allows us to capture characteristics of negation cues in Chinese using word-embedding information only. Not only does our model performs on par with previous work, further error analysis clarifies what problems remain to be addressed.