Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review

While reasoning capabilities typically emerge in large language models (LLMs) with tens of billions of parameters, recent research focuses on improving smaller open-source models through knowledge distillation (KD) from commercial LLMs. However, many of these studies rely solely on responses from a single LLM as the gold rationale, unlike the natural human learning process, which involves understanding both the correct answers and the reasons behind mistakes. In this paper, we introduce a novel Fault-Aware Distillation via Peer-Review (FAIR) approach: 1) Instead of merely obtaining gold rationales from teachers, our method asks teachers to identify and explain the student's mistakes, providing customized instruction learning data. 2) We design a simulated peer-review process between teacher LLMs, which selects only the generated rationales above the acceptance threshold. This reduces the chance of teachers guessing correctly with flawed rationale, improving instructional data quality. Comprehensive experiments and analysis on mathematical, commonsense, and logical reasoning tasks demonstrate the effectiveness of our method.

ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation

Reranking documents based on their relevance to a given query is critical in information retrieval. Traditional reranking methods often focus on improving the initial rankings but lack transparency, failing to explain why one document is ranked higher. In this paper, we introduce ReasoningRank, a novel reranking approach that enhances clarity by generating two types of reasoning: explicit reasoning, which explains how a document addresses the query, and comparison reasoning, which justifies the relevance of one document over another. We leverage large language models (LLMs) as teacher models to generate these explanations and distill this knowledge into smaller, more resource-efficient student models. While the student models may not outperform LLMs in speed, they significantly reduce the computational burden by requiring fewer resources, making them more suitable for large-scale or resource-constrained settings. These student models are trained to both generate meaningful reasoning and rerank documents, achieving competitive performance across multiple datasets, including MSMARCO and BRIGHT. Experiments demonstrate that ReasoningRank improves reranking accuracy and provides valuable insights into the decision-making process, offering a structured and interpretable solution for reranking tasks.

Enhance Reasoning by Learning from Mistakes: Peer-Review Knowledge Distillation from Multiple Large Language Models

Large language models (LLMs) have exhibited complex reasoning abilities by generating question rationales and demonstrated exceptional performance in natural language processing (NLP) tasks. However, these reasoning capabilities generally emerge in models with tens of billions of parameters, creating significant computational challenges for real-world deployment. Recent research has concentrated on improving open-source smaller models through knowledge distillation (KD) from commercial LLMs. Nevertheless, most of these studies rely solely on the responses from one single LLM as the gold rationale for training. In this paper, we introduce a novel Mistake-Aware Peer-Review Distillation (MAPD) approach: 1) Instead of merely obtaining gold rationales from teachers, our method asks teachers to identify and explain the student's mistakes, providing customized instruction learning data. 2) We design a simulated peer-review process between teacher LLMs, which selects only the generated rationales above the acceptance threshold. This reduces the chance of teachers guessing correctly with flawed rationale, improving instructional data quality. Comprehensive experiments and analysis on mathematical, commonsense, and logical reasoning tasks demonstrate the effectiveness of our method.

Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models

Phrases are fundamental linguistic units through which humans convey semantics. This study critically examines the capacity of API-based large language models (LLMs) to comprehend phrase semantics, utilizing three human-annotated datasets. We assess the performance of LLMs in executing phrase semantic reasoning tasks guided by natural language instructions and explore the impact of common prompting techniques, including few-shot demonstrations and Chain-of-Thought reasoning. Our findings reveal that LLMs greatly outperform traditional embedding methods across the datasets; however, they do not show a significant advantage over fine-tuned methods. The effectiveness of advanced prompting strategies shows variability. We conduct detailed error analyses to interpret the limitations faced by LLMs in comprehending phrase semantics. Code and data can be found at https://github.com/memray/llm_phrase_semantics.

RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts

This paper introduces the RAG-RLRC-LaySum framework, designed to make complex biomedical research understandable to laymen through advanced Natural Language Processing (NLP) techniques. Our Retrieval Augmented Generation (RAG) solution, enhanced by a reranking method, utilizes multiple knowledge sources to ensure the precision and pertinence of lay summaries. Additionally, our Reinforcement Learning for Readability Control (RLRC) strategy improves readability, making scientific content comprehensible to non-specialists. Evaluations using the publicly accessible PLOS and eLife datasets show that our methods surpass Plain Gemini model, demonstrating a 20% increase in readability scores, a 15% improvement in ROUGE-2 relevance scores, and a 10% enhancement in factual accuracy. The RAG-RLRC-LaySum framework effectively democratizes scientific knowledge, enhancing public engagement with biomedical discoveries.

Effects of Different Prompts on the Quality of GPT-4 Responses to Dementia Care Questions

Evidence suggests that different prompts lead large language models (LLMs) to generate responses with varying quality. Yet, little is known about prompts' effects on response quality in healthcare domains. In this exploratory study, we address this gap, focusing on a specific healthcare domain: dementia caregiving. We first developed an innovative prompt template with three components: (1) system prompts (SPs) featuring 4 different roles; (2) an initialization prompt; and (3) task prompts (TPs) specifying different levels of details, totaling 12 prompt combinations. Next, we selected 3 social media posts containing complicated, real-world questions about dementia caregivers' challenges in 3 areas: memory loss and confusion, aggression, and driving. We then entered these posts into GPT-4, with our 12 prompts, to generate 12 responses per post, totaling 36 responses. We compared the word count of the 36 responses to explore potential differences in response length. Two experienced dementia care clinicians on our team assessed the response quality using a rating scale with 5 quality indicators: factual, interpretation, application, synthesis, and comprehensiveness (scoring range: 0-5; higher scores indicate higher quality).

General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation

Training keyphrase generation (KPG) models requires a large amount of annotated data, which can be prohibitively expensive and often limited to specific domains. In this study, we first demonstrate that large distribution shifts among different domains severely hinder the transferability of KPG models. We then propose a three-stage pipeline, which gradually guides KPG models' learning focus from general syntactical features to domain-related semantics, in a data-efficient manner. With Domain-general Phrase pre-training, we pre-train Sequence-to-Sequence models with generic phrase annotations that are widely available on the web, which enables the models to generate phrases in a wide range of domains. The resulting model is then applied in the Transfer Labeling stage to produce domain-specific pseudo keyphrases, which help adapt models to a new domain. Finally, we fine-tune the model with limited data with true labels to fully adapt it to the target domain. Our experiment results show that the proposed process can produce good quality keyphrases in new domains and achieve consistent improvements after adaptation with limited in-domain annotated data.

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Faceted summarization provides briefings of a document from different perspectives. Readers can quickly comprehend the main points of a long document with the help of a structured outline. However, little research has been conducted on this subject, partially due to the lack of large-scale faceted summarization datasets. In this study, we present FacetSum, a faceted summarization benchmark built on Emerald journal articles, covering a diverse range of domains. Different from traditional document-summary pairs, FacetSum provides multiple summaries, each targeted at specific sections of a long document, including the purpose, method, findings, and value. Analyses and empirical results on our dataset reveal the importance of bringing structure into summaries. We believe FacetSum will spur further advances in summarization research and foster the development of NLP systems that can leverage the structured information in both long texts and summaries.

An Empirical Study on Neural Keyphrase Generation

Recent years have seen a flourishing of neural keyphrase generation works, including the release of several large-scale datasets and a host of new models to tackle them. Model performance on keyphrase generation tasks has increased significantly with evolving deep learning research. However, there lacks a comprehensive comparison among models, and an investigation on related factors (e.g., architectural choice, decoding strategy) that may affect a keyphrase generation system's performance. In this empirical study, we aim to fill this gap by providing extensive experimental results and analyzing the most crucial factors impacting the performance of keyphrase generation models. We hope this study can help clarify some of the uncertainties surrounding the keyphrase generation task and facilitate future research on this topic.

Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence

Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation. Existing studies concatenate target keyphrases in different orders but no study has examined the effects of ordering on models' behavior. In this paper, we propose several orderings for concatenation and inspect the important factors for training a successful keyphrase generation model. By running comprehensive comparisons, we observe one preferable ordering and summarize a number of empirical findings and challenges, which can shed light on future research on this line of work.