To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thinking'' really helpful? To analyze this, we conducted a quantitative meta-analysis covering over 100 papers using CoT and ran our own evaluations of 20 datasets across 14 models. Our results show that CoT gives strong performance benefits primarily on tasks involving math or logic, with much smaller gains on other types of tasks. On MMLU, directly generating the answer without CoT leads to almost identical accuracy as CoT unless the question or model's response contains an equals sign, indicating symbolic operations and reasoning. Following this finding, we analyze the behavior of CoT on these problems by separating planning and execution and comparing against tool-augmented LLMs. Much of CoT's gain comes from improving symbolic execution, but it underperforms relative to using a symbolic solver. Our results indicate that CoT can be applied selectively, maintaining performance while saving inference costs. Furthermore, they suggest a need to move beyond prompt-based CoT to new paradigms that better leverage intermediate computation across the whole range of LLM applications.

Learning to Refine with Fine-Grained Natural Language Feedback

Recent work has explored the capability of large language models (LLMs) to identify and correct errors in LLM-generated responses. These refinement approaches frequently evaluate what sizes of models are able to do refinement for what problems, but less attention is paid to what effective feedback for refinement looks like. In this work, we propose looking at refinement with feedback as a composition of three distinct LLM competencies: (1) identification of bad generations; (2) fine-grained natural language feedback generation; (3) refining with fine-grained feedback. The first step can be implemented with a high-performing discriminative model and steps 2 and 3 can be implemented either via prompted or fine-tuned LLMs. A key property of this approach is that the step 2 critique model can give fine-grained feedback about errors, made possible by offloading the discrimination to a separate model in step 1. We show that models of different capabilities benefit from refining with this approach on the task of improving factual consistency of document grounded summaries. Overall, our proposed method consistently outperforms existing end-to-end refinement approaches and current trained models not fine-tuned for factuality critiquing.

Using Natural Language Explanations to Rescale Human Judgments

The rise of large language models (LLMs) has brought a critical need for high-quality human-labeled data, particularly for processes like human feedback and evaluation. A common practice is to label data via consensus annotation over the judgments of multiple crowdworkers. However, different annotators may have different interpretations of labeling schemes unless given extensive training, and for subjective NLP tasks, even trained expert annotators can diverge heavily. We show that these nuances can be captured by high quality natural language explanations, and propose a method to rescale ordinal annotation in the presence of disagreement using LLMs. Specifically, we feed Likert ratings and corresponding natural language explanations into an LLM and prompt it to produce a numeric score. This score should reflect the underlying assessment of the example by the annotator. The presence of explanations allows the LLM to homogenize ratings across annotators in spite of scale usage differences. We explore our technique in the context of a document-grounded question answering task on which large language models achieve near-human performance. Among questions where annotators identify incompleteness in the answers, our rescaling improves correlation between nearly all annotator pairs, improving pairwise correlation on these examples by an average of 0.2 Kendall's tau.

Group Affect Prediction Using Multimodal Distributions

We describe our approach towards building an efficient predictive model to detect emotions for a group of people in an image. We have proposed that training a Convolutional Neural Network (CNN) model on the emotion heatmaps extracted from the image, outperforms a CNN model trained entirely on the raw images. The comparison of the models have been done on a recently published dataset of Emotion Recognition in the Wild (EmotiW) challenge, 2017. The proposed method achieved validation accuracy of 55.23% which is 2.44% above the baseline accuracy, provided by the EmotiW organizers.