$\texttt{LM}^\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning

Despite demonstrating emergent reasoning abilities, Large Language Models (LLMS) often lose track of complex, multi-step reasoning. Existing studies show that providing guidance via decomposing the original question into multiple subproblems elicits more robustness in LLM reasoning -- a decomposer generates the subproblems, and a solver solves each of these subproblems. However, these techniques fail to accommodate coordination between the decomposer and the solver modules (either in a single model or different specialized ones) -- the decomposer does not keep track of the ability of the solver to follow the decomposed reasoning. In this paper, we propose LM2 to address these challenges. LM2 modularizes the decomposition, solution, and verification into three different language models. The decomposer module identifies the key concepts necessary to solve the problem and generates step-by-step subquestions according to the reasoning requirement. The solver model generates the solution to the subproblems that are then checked by the verifier module; depending upon the feedback from the verifier, the reasoning context is constructed using the subproblems and the solutions. These models are trained to coordinate using policy learning. Exhaustive experimentation suggests the superiority of LM2 over existing methods on in- and out-domain reasoning problems, outperforming the best baselines by $8.1\%$ on MATH, $7.71\%$ on JEEBench, and $9.7\%$ on MedQA problems (code available at https://github.com/LCS2-IIITD/Language_Model_Multiplex).

Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation

The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically develop HINMIX, a parallel corpus of Hinglish to English, with ~4.2M sentence pairs. Subsequently, we propose RCMT, a robust perturbation based joint-training model that learns to handle noise in the real-world code-mixed text by parameter sharing across clean and noisy words. Further, we show the adaptability of RCMT in a zero-shot setup for Bengalish to English translation. Our evaluation and comprehensive analyses qualitatively and quantitatively demonstrate the superiority of RCMT over state-of-the-art code-mixed and robust translation methods.

Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: A Benchmark Study

Comprehensive summaries of sessions enable an effective continuity in mental health counseling, facilitating informed therapy planning. Yet, manual summarization presents a significant challenge, diverting experts' attention from the core counseling process. This study evaluates the effectiveness of state-of-the-art Large Language Models (LLMs) in selectively summarizing various components of therapy sessions through aspect-based summarization, aiming to benchmark their performance. We introduce MentalCLOUDS, a counseling-component guided summarization dataset consisting of 191 counseling sessions with summaries focused on three distinct counseling components (aka counseling aspects). Additionally, we assess the capabilities of 11 state-of-the-art LLMs in addressing the task of component-guided summarization in counseling. The generated summaries are evaluated quantitatively using standard summarization metrics and verified qualitatively by mental health professionals. Our findings demonstrate the superior performance of task-specific LLMs such as MentalLlama, Mistral, and MentalBART in terms of standard quantitative metrics such as Rouge-1, Rouge-2, Rouge-L, and BERTScore across all aspects of counseling components. Further, expert evaluation reveals that Mistral supersedes both MentalLlama and MentalBART based on six parameters -- affective attitude, burden, ethicality, coherence, opportunity costs, and perceived effectiveness. However, these models share the same weakness by demonstrating a potential for improvement in the opportunity costs and perceived effectiveness metrics.

SemEval 2024 -- Task 10: Emotion Discovery and Reasoning its Flip in Conversation (EDiReF)

We present SemEval-2024 Task 10, a shared task centred on identifying emotions and finding the rationale behind their flips within monolingual English and Hindi-English code-mixed dialogues. This task comprises three distinct subtasks - emotion recognition in conversation for code-mixed dialogues, emotion flip reasoning for code-mixed dialogues, and emotion flip reasoning for English dialogues. Participating systems were tasked to automatically execute one or more of these subtasks. The datasets for these tasks comprise manually annotated conversations focusing on emotions and triggers for emotion shifts (The task data is available at https://github.com/LCS2-IIITD/EDiReF-SemEval2024.git). A total of 84 participants engaged in this task, with the most adept systems attaining F1-scores of 0.70, 0.79, and 0.76 for the respective subtasks. This paper summarises the results and findings from 24 teams alongside their system descriptions.

How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning

Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT generation. This work investigates the neural sub-structures within LLMs that manifest CoT reasoning from a mechanistic point of view. From an analysis of LLaMA-2 7B applied to multistep reasoning over fictional ontologies, we demonstrate that LLMs deploy multiple parallel pathways of answer generation for step-by-step reasoning. These parallel pathways provide sequential answers from the input question context as well as the generated CoT. We observe a striking functional rift in the middle layers of the LLM. Token representations in the initial half remain strongly biased towards the pretraining prior, with the in-context taking over abruptly in the later half. This internal phase shift manifests in different functional components: attention heads that write the answer token predominantly appear in the later half, attention heads that move information along ontological relationships appear exclusively in the initial half, and so on. To the best of our knowledge, this is the first attempt towards mechanistic investigation of CoT reasoning in LLMs.

FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models

Taxonomies represent an arborescence hierarchical structure that establishes relationships among entities to convey knowledge within a specific domain. Each edge in the taxonomy signifies a hypernym-hyponym relationship. Taxonomies find utility in various real-world applications, such as e-commerce search engines and recommendation systems. Consequently, there arises a necessity to enhance these taxonomies over time. However, manually curating taxonomies with neoteric data presents challenges due to limitations in available human resources and the exponential growth of data. Therefore, it becomes imperative to develop automatic taxonomy expansion methods. Traditional supervised taxonomy expansion approaches encounter difficulties stemming from limited resources, primarily due to the small size of existing taxonomies. This scarcity of training data often leads to overfitting. In this paper, we propose FLAME, a novel approach for taxonomy expansion in low-resource environments by harnessing the capabilities of large language models that are trained on extensive real-world knowledge. LLMs help compensate for the scarcity of domain-specific knowledge. Specifically, FLAME leverages prompting in few-shot settings to extract the inherent knowledge within the LLMs, ascertaining the hypernym entities within the taxonomy. Furthermore, it employs reinforcement learning to fine-tune the large language models, resulting in more accurate predictions. Experiments on three real-world benchmark datasets demonstrate the effectiveness of FLAME in real-world scenarios, achieving a remarkable improvement of 18.5% in accuracy and 12.3% in Wu & Palmer metric over eight baselines. Furthermore, we elucidate the strengths and weaknesses of FLAME through an extensive case study, error analysis and ablation studies on the benchmarks.

Probing Critical Learning Dynamics of PLMs for Hate Speech Detection

Despite the widespread adoption, there is a lack of research into how various critical aspects of pretrained language models (PLMs) affect their performance in hate speech detection. Through five research questions, our findings and recommendations lay the groundwork for empirically investigating different aspects of PLMs' use in hate speech detection. We deep dive into comparing different pretrained models, evaluating their seed robustness, finetuning settings, and the impact of pretraining data collection time. Our analysis reveals early peaks for downstream tasks during pretraining, the limited benefit of employing a more recent pretraining corpus, and the significance of specific layers during finetuning. We further call into question the use of domain-specific models and highlight the need for dynamic datasets for benchmarking hate speech detection.

Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models

In the evolving landscape of online communication, moderating hate speech (HS) presents an intricate challenge, compounded by the multimodal nature of digital content. This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs). Our exploration begins with a thorough analysis of current literature, revealing the nuanced interplay between textual, visual, and auditory elements in propagating HS. We uncover a notable trend towards integrating these modalities, primarily due to the complexity and subtlety with which HS is disseminated. A significant emphasis is placed on the advances facilitated by LLMs and LMMs, which have begun to redefine the boundaries of detection and moderation capabilities. We identify existing gaps in research, particularly in the context of underrepresented languages and cultures, and the need for solutions to handle low-resource settings. The survey concludes with a forward-looking perspective, outlining potential avenues for future research, including the exploration of novel AI methodologies, the ethical governance of AI in moderation, and the development of more nuanced, context-aware systems. This comprehensive overview aims to catalyze further research and foster a collaborative effort towards more sophisticated, responsible, and human-centric approaches to HS moderation in the digital era. WARNING: This paper contains offensive examples.

Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues

Code-mixing, the blending of multiple languages within a single conversation, introduces a distinctive challenge, particularly in the context of response generation. Capturing the intricacies of code-mixing proves to be a formidable task, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. In this study, we explore response generation within code-mixed conversations. We introduce a novel approach centered on harnessing the Big Five personality traits acquired in an unsupervised manner from the conversations to bolster the performance of response generation. These inferred personality attributes are seamlessly woven into the fabric of the dialogue context, using a novel fusion mechanism, PA3. It uses an effective two-step attention formulation to fuse the dialogue and personality information. This fusion not only enhances the contextual relevance of generated responses but also elevates the overall performance of the model. Our experimental results, grounded in a dataset comprising of multi-party Hindi-English code-mix conversations, highlight the substantial advantages offered by personality-infused models over their conventional counterparts. This is evident in the increase observed in ROUGE and BLUE scores for the response generation task when the identified personality is seamlessly integrated into the dialogue context. Qualitative assessment for personality identification and response generation aligns well with our quantitative results.