Pei Zhou

Pei Zhou, Aman Madaan, Srividya Pranavi Potharaju et al. · cmu

"Thinking is for Doing." Humans can infer other people's mental states from observations--an ability called Theory-of-Mind (ToM)--and subsequently act pragmatically on those inferences. Existing question answering benchmarks such as ToMi ask models questions to make inferences about beliefs of characters in a story, but do not test whether models can then use these inferences to guide their actions. We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenarios. Experiments on T4D demonstrate that LLMs such as GPT-4 and PaLM 2 seemingly excel at tracking characters' beliefs in stories, but they struggle to translate this capability into strategic action. Our analysis reveals the core challenge for LLMs lies in identifying the implicit inferences about mental states without being explicitly asked about as in ToMi, that lead to choosing the correct action in T4D. To bridge this gap, we introduce a zero-shot prompting framework, Foresee and Reflect (FaR), which provides a reasoning structure that encourages LLMs to anticipate future challenges and reason about potential actions. FaR boosts GPT-4's performance from 50% to 71% on T4D, outperforming other prompting methods such as Chain-of-Thought and Self-Ask. Moreover, FaR generalizes to diverse out-of-distribution story structures and scenarios that also require ToM inferences to choose an action, consistently outperforming other methods including few-shot in-context learning.

Pranjal Aggarwal, Aman Madaan, Ankit Anand et al. · cmu

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and performance remains challenging. In this work, we present Automix, an approach that strategically routes queries to larger LMs, based on the approximate correctness of outputs from a smaller LM. Central to Automix are two key technical contributions. First, it has a few-shot self-verification mechanism, which estimates the reliability of its own outputs without requiring extensive training. Second, given that self-verification can be noisy, it employs a POMDP based router that can effectively select an appropriately sized model, based on answer confidence. Experiments across five language models and five challenging datasets show that Automix consistently surpasses strong baselines, reducing computational cost by over 50% for comparable performance.

Taiwei Shi, Zhuoer Wang, Longqi Yang et al. · amazon-science, microsoft-research

As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource-intensive nature, inherent subjectivity, misalignment with real-world user preferences, and the risk of feedback loops that amplify model biases. To overcome these limitations, we introduce WildFeedback, a novel framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically. Given a corpus of multi-turn user-LLM conversation, WildFeedback identifies and classifies user feedback to LLM responses between conversation turns. The user feedback is then used to create examples of preferred and dispreferred responses according to users' preference. Our experiments demonstrate that LLMs fine-tuned on WildFeedback dataset exhibit significantly improved alignment with user preferences, as evidenced by both traditional benchmarks and our proposed checklist-guided evaluation. By incorporating in-situ feedback from actual users, WildFeedback addresses the scalability, subjectivity, and bias challenges that plague existing approaches, marking a significant step toward developing LLMs that are more responsive to the diverse and evolving needs of their users.

Pei Zhou, Jay Pujara, Xiang Ren et al.

We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery process where LLMs select multiple atomic reasoning modules such as critical thinking and step-by-step thinking, and compose them into an explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER substantially improves GPT-4 and PaLM 2's performance on challenging reasoning benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER outperforms inference-intensive methods such as CoT-Self-Consistency by more than 20%, while requiring 10-40x fewer inference compute. Finally, we show that the self-discovered reasoning structures are universally applicable across model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share commonalities with human reasoning patterns.

Lei Sun, Hang Guo, Bin Ren et al.

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (σ = 50), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on computational complexity or model size. The task assumes independent additive white Gaussian noise (AWGN) with a fixed noise level of 50. A total of 290 participants registered for the challenge, with 20 teams successfully submitting valid results, providing insights into the current state-of-the-art in image denoising.

Jie He, Jennifer Neville, Mengting Wan et al.

Large Language Models (LLMs) can enhance their capabilities as AI assistants by integrating external tools, allowing them to access a wider range of information. While recent LLMs are typically fine-tuned with tool usage examples during supervised fine-tuning (SFT), questions remain about their ability to develop robust tool-usage skills and can effectively generalize to unseen queries and tools. In this work, we present GenTool, a novel training framework that prepares LLMs for diverse generalization challenges in tool utilization. Our approach addresses two fundamental dimensions critical for real-world applications: Zero-to-One Generalization, enabling the model to address queries initially lacking a suitable tool by adopting and utilizing one when it becomes available, and Weak-to-Strong Generalization, allowing models to leverage enhanced versions of existing tools to solve queries. To achieve this, we develop synthetic training data simulating these two dimensions of tool usage and introduce a two-stage fine-tuning approach: optimizing tool ranking, then refining tool selection. Through extensive experiments across four generalization scenarios, we demonstrate that our method significantly enhances the tool-usage capabilities of LLMs ranging from 1B to 8B parameters, achieving performance that surpasses GPT-4o. Furthermore, our analysis also provides valuable insights into the challenges LLMs encounter in tool generalization.

Shuaiqi Wang, Vikas Raunak, Arturs Backurs et al.

Differentially private (DP) synthetic data generation is a promising technique for utilizing private datasets that otherwise cannot be exposed for model training or other analytics. While much research literature has focused on generating private unstructured text and image data, in enterprise settings, structured data (e.g., tabular) is more common, often including natural language fields or components. Existing synthetic data evaluation techniques (e.g., FID) struggle to capture the structural properties and correlations of such datasets. In this work, we propose Struct-Bench, a framework and benchmark for evaluating synthetic datasets derived from structured datasets that contain natural language data. The Struct-Bench framework requires users to provide a representation of their dataset structure as a Context-Free Grammar (CFG). Our benchmark comprises 5 real-world and 2 synthetically generated datasets, each annotated with CFGs. We show that these datasets demonstrably present a great challenge even for state-of-the-art DP synthetic data generation methods. Struct-Bench also includes reference implementations of different metrics and a leaderboard, thereby providing researchers a standardized evaluation platform to benchmark and investigate privacy-preserving synthetic data generation methods. Further, we also present a case study showing how to use Struct-Bench to improve the synthetic data quality of Private Evolution (PE) on structured data. The benchmark and the leaderboard have been publicly made available at https://struct-bench.github.io.

Ziyi Liu, Abhishek Anand, Pei Zhou et al.

Large language models (LLMs) have demonstrated the potential to mimic human social intelligence. However, most studies focus on simplistic and static self-report or performance-based tests, which limits the depth and validity of the analysis. In this paper, we developed a novel framework, InterIntent, to assess LLMs' social intelligence by mapping their ability to understand and manage intentions in a game setting. We focus on four dimensions of social intelligence: situational awareness, self-regulation, self-awareness, and theory of mind. Each dimension is linked to a specific game task: intention selection, intention following, intention summarization, and intention guessing. Our findings indicate that while LLMs exhibit high proficiency in selecting intentions, achieving an accuracy of 88%, their ability to infer the intentions of others is significantly weaker, trailing human performance by 20%. Additionally, game performance correlates with intention understanding, highlighting the importance of the four components towards success in this game. These findings underline the crucial role of intention understanding in evaluating LLMs' social intelligence and highlight the potential of using social deduction games as a complex testbed to enhance LLM evaluation. InterIntent contributes a structured approach to bridging the evaluation gap in social intelligence within multiplayer games.

Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia et al.

Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing the right answer from a set of candidates, and do not involve interactive language generation as in dialogue. Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet. In this paper, we present an empirical study of commonsense in dialogue response generation. We first auto-extract commonsensical dialogues from existing dialogue datasets by leveraging ConceptNet, a commonsense knowledge graph. Furthermore, building on social contexts/situations in SocialIQA, we collect a new dialogue dataset with 25K dialogues aimed at exhibiting social commonsense in an interactive setting. We evaluate response generation models trained using these datasets and find that models trained on both extracted and our collected data produce responses that consistently exhibit more commonsense than baselines. Finally we propose an approach for automatic evaluation of commonsense that relies on features derived from ConceptNet and pre-trained language and dialog models, and show reasonable correlation with human evaluation of responses' commonsense quality. We are releasing a subset of our collected data, Commonsense-Dialogues, containing about 11K dialogs.

Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan et al.

Pretrained language models have demonstrated outstanding performance in many NLP tasks recently. However, their social intelligence, which requires commonsense reasoning about the current situation and mental states of others, is still developing. Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning. Building on top of the pretrained RoBERTa and GPT2 models, we propose several architecture variations and extensions, as well as leveraging external commonsense corpora, to optimize the model for Social IQA. Our proposed system achieves competitive results as those top-ranking models on the leaderboard. This work demonstrates the strengths of pretrained language models, and provides viable ways to improve their performance for a particular task.

Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan et al.

Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory. To enable this, machines need to have a more general understanding of our complicated world and develop the ability to perform commonsense reasoning besides fitting the specific downstream tasks. External commonsense knowledge graphs (KGs), such as ConceptNet, provide rich information about words and their relationships. Thus, towards general commonsense learning, we propose two approaches to \emph{implicitly} and \emph{explicitly} infuse such KGs into pretrained language models. We demonstrate our proposed methods perform well on SocialIQA, a social commonsense reasoning task, in both limited and full training data regimes.

Pei Zhou, Pegah Jandaghi, Bill Yuchen Lin et al.

Humans use commonsense reasoning (CSR) implicitly to produce natural and coherent responses in conversations. Aiming to close the gap between current response generation (RG) models and human communication abilities, we want to understand why RG models respond as they do by probing RG model's understanding of commonsense reasoning that elicits proper responses. We formalize the problem by framing commonsense as a latent variable in the RG task and using explanations for responses as textual form of commonsense. We collect 6k annotated explanations justifying responses from four dialogue datasets and ask humans to verify them and propose two probing settings to evaluate RG models' CSR capabilities. Probing results show that models fail to capture the logical relations between commonsense explanations and responses and fine-tuning on in-domain data and increasing model sizes do not lead to understanding of CSR for RG. We hope our study motivates more research in making RG models emulate the human reasoning process in pursuit of smooth human-AI communication.

Ninareh Mehrabi, Pei Zhou, Fred Morstatter et al.

Warning: this paper contains content that may be offensive or upsetting. Numerous natural language processing models have tried injecting commonsense by using the ConceptNet knowledge base to improve performance on different tasks. ConceptNet, however, is mostly crowdsourced from humans and may reflect human biases such as "lawyers are dishonest." It is important that these biases are not conflated with the notion of commonsense. We study this missing yet important problem by first defining and quantifying biases in ConceptNet as two types of representational harms: overgeneralization of polarized perceptions and representation disparity. We find that ConceptNet contains severe biases and disparities across four demographic categories. In addition, we analyze two downstream models that use ConceptNet as a source for commonsense knowledge and find the existence of biases in those models as well. We further propose a filtered-based bias-mitigation approach and examine its effectiveness. We show that our mitigation approach can reduce the issues in both resource and models but leads to a performance drop, leaving room for future work to build fairer and stronger commonsense models.

Pei Zhou, Rahul Khanna, Seyeon Lee et al.

Pre-trained language models (PTLMs) have achieved impressive performance on commonsense inference benchmarks, but their ability to employ commonsense to make robust inferences, which is crucial for effective communications with humans, is debated. In the pursuit of advancing fluid human-AI communication, we propose a new challenge, RICA: Robust Inference capability based on Commonsense Axioms, that evaluates robust commonsense inference despite textual perturbations. To generate data for this challenge, we develop a systematic and scalable procedure using commonsense knowledge bases and probe PTLMs across two different evaluation settings. Extensive experiments on our generated probe sets with more than 10k statements show that PTLMs perform no better than random guessing on the zero-shot setting, are heavily impacted by statistical biases, and are not robust to perturbation attacks. We also find that fine-tuning on similar statements offer limited gains, as PTLMs still fail to generalize to unseen inferences. Our new large-scale benchmark exposes a significant gap between PTLMs and human-level language understanding and offers a new challenge for PTLMs to demonstrate commonsense.

Bill Yuchen Lin, Wangchunshu Zhou, Ming Shen et al.

Recently, large-scale pre-trained language models have demonstrated impressive performance on several commonsense-reasoning benchmark datasets. However, building machines with commonsense to compose realistically plausible sentences remains challenging. In this paper, we present a constrained text generation task, CommonGen associated with a benchmark dataset, to explicitly test machines for the ability of generative commonsense reasoning. Given a set of common concepts (e.g., {dog, frisbee, catch, throw}); the task is to generate a coherent sentence describing an everyday scenario using these concepts (e.g., "a man throws a frisbee and his dog catches it"). The CommonGen task is challenging because it inherently requires 1) relational reasoning with background commonsense knowledge, and 2) compositional generalization ability to work on unseen concept combinations. Our dataset, constructed through a combination of crowdsourced and existing caption corpora, consists of 79k commonsense descriptions over 35k unique concept-sets. Experiments show that there is a large gap between state-of-the-art text generation models (e.g., T5) and human performance. Furthermore, we demonstrate that the learned generative commonsense reasoning capability can be transferred to improve downstream tasks such as CommonsenseQA by generating additional context.

Weijia Shi, Muhao Chen, Pei Zhou et al.

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized embedding of a word changes drastically when the context is paraphrased. As a result, the downstream model is not robust to paraphrasing and other linguistic variations. To enhance the stability of contextualized word embedding models, we propose an approach to retrofitting contextualized embedding models with paraphrase contexts. Our method learns an orthogonal transformation on the input space, which seeks to minimize the variance of word representations on paraphrased contexts. Experiments show that the retrofitted model significantly outperforms the original ELMo on various sentence classification and language inference tasks.

Pei Zhou, Weijia Shi, Jieyu Zhao et al.

Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly extended to languages that exhibit morphological agreement on gender, such as Spanish and French. In this paper, we propose new metrics for evaluating gender bias in word embeddings of these languages and further demonstrate evidence of gender bias in bilingual embeddings which align these languages with English. Finally, we extend an existing approach to mitigate gender bias in word embeddings under both monolingual and bilingual settings. Experiments on modified Word Embedding Association Test, word similarity, word translation, and word pair translation tasks show that the proposed approaches effectively reduce the gender bias while preserving the utility of the embeddings.

Pei Zhou, Muhao Chen, Kai-Wei Chang et al.

Quantifying differences in terminologies from various academic domains has been a longstanding problem yet to be solved. We propose a computational approach for analyzing linguistic variation among scientific research fields by capturing the semantic change of terms based on a neural language model. The model is trained on a large collection of literature in five computer science research fields, for which we obtain field-specific vector representations for key terms, and global vector representations for other words. Several quantitative approaches are introduced to identify the terms whose semantics have drastically changed, or remain unchanged across different research fields. We also propose a metric to quantify the overall linguistic variation of research fields. After quantitative evaluation on human annotated data and qualitative comparison with other methods, we show that our model can improve cross-disciplinary data collaboration by identifying terms that potentially induce confusion during interdisciplinary studies.