arXiv subjects

Zhijing Jin

Publications and source records attributed to Zhijing Jin.

At least 55 records · Page 3Linked to original sources

arXiv2026

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests

Large language models (LLMs) are increasingly deployed in contexts where their failures can have direct sociopolitical consequences. Yet, existing safety benchmarks rarely test vulnerabilities in domains such as political manipulation, propaganda and disinformation generation, or surveillance and information control. We introduce SocialHarmBench, a dataset of 585 prompts spanning 7 sociopolitical categories and 34 countries, designed to surface where LLMs most acutely fail in politically charged contexts. Our evaluations reveal several shortcomings: open-weight models exhibit high vulnerability to harmful compliance, with Mistral-7B reaching attack success rates as high as 97% to 98% in domains such as historical revisionism, propaganda, and political manipulation. Moreover, temporal and geographic analyses show that LLMs are most fragile when confronted with 21st-century or pre-20th-century contexts, and when responding to prompts tied to regions such as Latin America, the USA, and the UK. These findings demonstrate that current safeguards fail to generalize to high-stakes sociopolitical settings, exposing systematic biases and raising concerns about the reliability of LLMs in preserving human rights and democratic values. We share the SocialHarmBench benchmark at https://huggingface.co/datasets/psyonp/SocialHarmBench.

cs.CL↗

arXiv2026

Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models

Large language models (LLMs) are increasingly used as sources of historical information, motivating the need for scalable audits on contested events and politically charged narratives in settings that mirror real user interactions. We introduce \texttt{HistoricalMisinfo, a curated dataset of $500$ contested events from $45$ countries, each paired with a factual reference narrative and a documented revisionist reference narrative. To approximate real-world usage, we instantiate each event in $11$ prompt scenarios that reflect common communication settings (e.g., questions, textbooks, social posts, policy briefs). Using an LLM-as-a-judge protocol that compares model outputs to the two references, we evaluate LLMs varying across model architectures in two conditions: (i) neutral user prompts that ask for factually accurate information, and (ii) robustness prompts in which the user explicitly requests the revisionist version of the event. Under neutral prompts, models are generally closer to factual references, though the resulting scores should be interpreted as reference-alignment signals rather than definitive evidence of human-interpretable revisionism. Robustness prompting yields a strong and consistent effect: when the user requests the revisionist narrative, all evaluated models show sharply higher revisionism scores, indicating limited resistance or self-correction. HistoricalMisinfo provides a practical foundation for benchmarking robustness to revisionist framing and for guiding future work on more precise automatic evaluation of contested historical claims to ensure a sustainable integration of AI systems within society. Our code is available at https://github.com/francescortu/PreservingHistoricalTruth

cs.CY↗

arXiv2026

Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does performance favor the dominant training language? To address this, we train models on different multilingual mixtures and analyze their internal mechanisms using Cross-Layer Transcoders (CLTs) and Attribution Graphs. Our results reveal multilingual shared representations: the model employs highly similar features across languages, while language-specific decoding emerges in later layers. Training models without English shows identical multilingual shared space structures. Decoding relies partly on a small set of high-frequency features in the final layers, which linearly encode language identity from early layers. Intervening on these features allows one language to be suppressed and another substituted. Finally, to explain non-English failures, we perform a Model-Diffing experiment: underperformance arises from dim late-layer features, weak middle-layer clusters, and tokenizer bias toward English that forces early layers to specialize in word reassembly. Finetuning strengthens these features and their links, improving token assembly and language-specific decoding, providing a mechanistic explanation for multilingual gaps. Our models and CLTs are available at https://huggingface.co/collections/CausalNLP/multilingual-clts and https://huggingface.co/collections/CausalNLP/multilingual-gpt2-models. Our code is available at: https://github.com/abirharrasse/MultilingualCLTs

cs.CL↗

arXiv2026

BinaryPPO: Efficient Policy Optimization for Binary Classification

Supervised fine-tuning (SFT) is the standard approach for binary classification tasks such as toxicity detection, factuality verification, and causal inference. However, SFT often performs poorly in real-world settings with label noise, class imbalance, or sparse supervision. We introduce BinaryPPO, an offline reinforcement learning large language model (LLM) framework that reformulates binary classification as a reward maximization problem. Our method leverages a variant of Proximal Policy Optimization (PPO) with a confidence-weighted reward function that penalizes uncertain or incorrect predictions, enabling the model to learn robust decision policies from static datasets without online interaction. Across eight domain-specific benchmarks and multiple models with differing architectures, BinaryPPO improves accuracy by 40-60 percentage points, reaching up to 99%, substantially outperforming supervised baselines. We provide an in-depth analysis of the role of reward shaping, advantage scaling, and policy stability in enabling this improvement. Overall, we demonstrate that confidence-based reward design provides a robust alternative to SFT for binary classification. Our code is available at https://github.com/psyonp/BinaryPPO.

cs.LG↗

arXiv2026

Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification

Large language models (LLMs) are increasingly being applied to tasks that involve causal reasoning. However, current benchmarks often rely on string matching or surface-level metrics that do not capture whether the output of a model is formally valid under the semantics of causal reasoning. To address this, we propose DoVerifier, a simple symbolic verifier that checks whether LLM-generated causal expressions are derivable from a given causal graph using rules from do-calculus and probability theory. This allows us to recover correct answers to causal queries that would otherwise be marked incorrect due to superficial differences in their causal semantics. Our evaluations on synthetic data and causal QA benchmarks show that DoVerifier more accurately captures semantic correctness of causal reasoning traces, offering a more rigorous and informative way to evaluate LLMs on causal reasoning.

cs.AI↗

arXiv2026

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment

Natural language processing (NLP) now shapes many aspects of our world, yet its potential for positive social impact is underexplored. This paper surveys work in ``NLP for Social Good" (NLP4SG) across nine domains relevant to global development and risk agendas, summarizing principal tasks and challenges. We analyze ACL Anthology trends, finding that inclusion and AI harms attract the most research, while domains such as poverty, peacebuilding, and environmental protection remain underexplored. Guided by our review, we outline opportunities for responsible and equitable NLP and conclude with a call for cross-disciplinary partnerships and human-centered approaches to ensure that future NLP technologies advance the public good.

cs.CL↗

arXiv2025

Improving Large Language Model Safety with Contrastive Representation Learning

Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle to generalize across varying attack types, recent advancements in representation engineering offer promising alternatives. In this work, we propose a defense framework that formulates model defense as a contrastive representation learning (CRL) problem. Our method finetunes a model using a triplet-based loss combined with adversarial hard negative mining to encourage separation between benign and harmful representations. Our experimental results across multiple models demonstrate that our approach outperforms prior representation engineering-based defenses, improving robustness against both input-level and embedding-space attacks without compromising standard performance. Our code is available at https://github.com/samuelsimko/crl-llm-defense

cs.CL↗

arXiv2025

Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models

As Large Language Models (LLMs) become increasingly integrated into everyday life and information ecosystems, concerns about their implicit biases continue to persist. While prior work has primarily examined socio-demographic and left--right political dimensions, little attention has been paid to how LLMs align with broader geopolitical value systems, particularly the democracy--authoritarianism spectrum. In this paper, we propose a novel methodology to assess such alignment, combining (1) the F-scale, a psychometric tool for measuring authoritarian tendencies, (2) FavScore, a newly introduced metric for evaluating model favorability toward world leaders, and (3) role-model probing to assess which figures are cited as general role-models by LLMs. We find that LLMs generally favor democratic values and leaders, but exhibit increased favorability toward authoritarian figures when prompted in Mandarin. Further, models are found to often cite authoritarian figures as role models, even outside explicit political contexts. These results shed light on ways LLMs may reflect and potentially reinforce global political ideologies, highlighting the importance of evaluating bias beyond conventional socio-political axes. Our code is available at: https://github.com/irenestrauss/Democratic-Authoritarian-Bias-LLMs.

cs.CL↗

arXiv2025

Are LLMs Good Safety Agents or a Propaganda Engine?

Large Language Models (LLMs) are trained to refuse to respond to harmful content. However, systematic analyses of whether this behavior is truly a reflection of its safety policies or an indication of political censorship, that is practiced globally by countries, is lacking. Differentiating between safety influenced refusals or politically motivated censorship is hard and unclear. For this purpose we introduce PSP, a dataset built specifically to probe the refusal behaviors in LLMs from an explicitly political context. PSP is built by formatting existing censored content from two data sources, openly available on the internet: sensitive prompts in China generalized to multiple countries, and tweets that have been censored in various countries. We study: 1) impact of political sensitivity in seven LLMs through data-driven (making PSP implicit) and representation-level approaches (erasing the concept of politics); and, 2) vulnerability of models on PSP through prompt injection attacks (PIAs). Associating censorship with refusals on content with masked implicit intent, we find that most LLMs perform some form of censorship. We conclude with summarizing major attributes that can cause a shift in refusal distributions across models and contexts of different countries.

cs.CL↗

arXiv2025

Taming Object Hallucinations with Verified Atomic Confidence Estimation

Multimodal Large Language Models (MLLMs) often suffer from hallucinations, particularly errors in object existence, attributes, or relations, which undermine their reliability. We introduce TACO (Verified Atomic Confidence Estimation), a simple framework that mitigates hallucinations through self-verification and confidence calibration without relying on external vision experts. TACO decomposes responses into atomic queries, paraphrases them to reduce sensitivity to wording, and estimates confidence using self-consistency (black-box) or self-confidence (gray-box) aggregation, before refining answers with a language model. Experiments on five benchmarks (POPE, MME, HallusionBench, AMBER, and MM-Hal Bench) with two MLLMs (\texttt{LLaVA-1.5-7B} and \texttt{CogVLM2}) show that TACO consistently outperforms direct prompting and Visual Contrastive Decoding, reduces systematic biases, and improves confidence calibration, demonstrating its effectiveness in enhancing the faithfulness of MLLMs.

cs.CV↗

arXiv2025

Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries

Recent progress in Large Language Model (LLM) technology has changed our role in interacting with these models. Instead of primarily testing these models with questions we already know answers to, we are now using them for queries where the answers are unknown to us, driven by human curiosity. This shift highlights the growing need to understand curiosity-driven human questions - those that are more complex, open-ended, and reflective of real-world needs. To this end, we present Quriosity, a collection of 13.5K naturally occurring questions from three diverse sources: human-to-search-engine queries, human-to-human interactions, and human-to-LLM conversations. Our comprehensive collection enables a rich understanding of human curiosity across various domains and contexts. Our analysis reveals a significant presence of causal questions (up to 42%) in the dataset, for which we develop an iterative prompt improvement framework to identify all causal queries and examine their unique linguistic properties, cognitive complexity and source distribution. Our paper paves the way for future work on causal question identification and open-ended chatbot interactions. Our code and data are at https://github.com/roberto-ceraolo/quriosity.

cs.CL↗

arXiv2025

The Curious Case of Curiosity across Human Cultures and LLMs

Recent advances in Large Language Models (LLMs) have expanded their role in human interaction, yet curiosity -- a central driver of inquiry -- remains underexplored in these systems, particularly across cultural contexts. In this work, we investigate cultural variation in curiosity using Yahoo! Answers, a real-world multi-country dataset spanning diverse topics. We introduce CUEST (CUriosity Evaluation across SocieTies), an evaluation framework that measures human-model alignment in curiosity through linguistic (style), topic preference (content) analysis and grounding insights in social science constructs. Across open- and closed-source models, we find that LLMs flatten cross-cultural diversity, aligning more closely with how curiosity is expressed in Western countries. We then explore fine-tuning strategies to induce curiosity in LLMs, narrowing the human-model alignment gap by up to 50%. Finally, we demonstrate the practical value of curiosity for LLM adaptability across cultures, showing its importance for future NLP research.

cs.CL↗

arXiv2025

Are Language Models Consequentialist or Deontological Moral Reasoners?

As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has mainly examined the moral judgments in large language models (LLMs), rather than their underlying moral reasoning process. In contrast, we focus on a large-scale analysis of the moral reasoning traces provided by LLMs. Furthermore, unlike prior work that attempted to draw inferences from only a handful of moral dilemmas, our study leverages over 600 distinct trolley problems as probes for revealing the reasoning patterns that emerge within different LLMs. We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology. Our analysis reveals that LLM chains-of-thought tend to favor deontological principles based on moral obligations, while post-hoc explanations shift notably toward consequentialist rationales that emphasize utility. Our framework provides a foundation for understanding how LLMs process and articulate ethical considerations, an important step toward safe and interpretable deployment of LLMs in high-stakes decision-making environments. Our code is available at https://github.com/keenansamway/moral-lens .

cs.CL↗

arXiv2025

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models

As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust safety. While prior work has extensively studied situational awareness which refers to an LLM's ability to recognize its operating phase and constraints, it has largely overlooked the complementary capacity to identify and adapt to the identity and characteristics of a dialogue partner. In this paper, we formalize this latter capability as interlocutor awareness and present the first systematic evaluation of its emergence in contemporary LLMs. We examine interlocutor inference across three dimensions-reasoning patterns, linguistic style, and alignment preferences-and show that LLMs reliably identify same-family peers and certain prominent model families, such as GPT and Claude. To demonstrate its practical significance, we develop three case studies in which interlocutor awareness both enhances multi-LLM collaboration through prompt adaptation and introduces new alignment and safety vulnerabilities, including reward-hacking behaviors and increased jailbreak susceptibility. Our findings highlight the dual promise and peril of identity-sensitive behavior in LLMs, underscoring the need for further understanding of interlocutor awareness and new safeguards in multi-agent deployments. Our code is open-sourced at https://github.com/younwoochoi/InterlocutorAwarenessLLM.

cs.CL↗

arXiv2025

Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias

Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. This paper introduces a causal formulation for bias measurement in generative language models. Based on this theoretical foundation, we outline a list of desiderata for designing robust bias benchmarks. We then propose a benchmark called OccuGender, with a bias-measuring procedure to investigate occupational gender bias. We test several state-of-the-art open-source LLMs on OccuGender, including Llama, Mistral, and their instruction-tuned versions. The results show that these models exhibit substantial occupational gender bias. Lastly, we discuss prompting strategies for bias mitigation and an extension of our causal formulation to illustrate the generalizability of our framework. Our code and data https://github.com/chenyuen0103/gender-bias.

cs.CL↗

arXiv2025

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding their cooperation and social mechanisms is becoming increasingly important. In particular, how LLMs balance self-interest and collective well-being is a critical challenge for ensuring alignment, robustness, and safe deployment. In this paper, we examine the challenge of costly sanctioning in multi-agent LLM systems, where an agent must decide whether to invest its own resources to incentivize cooperation or penalize defection. To study this, we adapt a public goods game with institutional choice from behavioral economics, allowing us to observe how different LLMs navigate social dilemmas over repeated interactions. Our analysis reveals four distinct behavioral patterns among models: some consistently establish and sustain high levels of cooperation, others fluctuate between engagement and disengagement, some gradually decline in cooperative behavior over time, and others rigidly follow fixed strategies regardless of outcomes. Surprisingly, we find that reasoning LLMs, such as the o1 series, struggle significantly with cooperation, whereas some traditional LLMs consistently achieve high levels of cooperation. These findings suggest that the current approach to improving LLMs, which focuses on enhancing their reasoning capabilities, does not necessarily lead to cooperation, providing valuable insights for deploying LLM agents in environments that require sustained collaboration. Our code is available at https://github.com/davidguzmanp/SanctSim

cs.AI↗

arXiv2025

Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification

We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models (LLMs). Co-DETECT starts with an initial, sketch-level codebook and dataset provided by a domain expert, then leverages the LLM to annotate the data and identify edge cases that are not well described by the initial codebook. Specifically, Co-DETECT flags challenging examples, induces high-level, generalizable descriptions of edge cases, and assists user in incorporating edge case handling rules to improve the codebook. This iterative process enables more effective handling of nuanced phenomena through compact, generalizable annotation rules. Extensive user study, qualitative and quantitative analyses prove the effectiveness of Co-DETECT.

cs.CL↗

arXiv2025

Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness

The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhanced problem-solving. These multi-agent debate (MAD) approaches, where agents collaboratively present, critique, and refine arguments, potentially offer improved reasoning, robustness, and diverse perspectives over monolithic models. Despite prior studies leveraging MAD, a systematic understanding of its effectiveness compared to self-agent methods, particularly under varying conditions, remains elusive. This paper seeks to fill this gap by conceptualizing MAD as a test-time computational scaling technique, distinguished by collaborative refinement and diverse exploration capabilities. We conduct a comprehensive empirical investigation comparing MAD with strong self-agent test-time scaling baselines on mathematical reasoning and safety-related tasks. Our study systematically examines the influence of task difficulty, model scale, and agent diversity on MAD's performance. Key findings reveal that, for mathematical reasoning, MAD offers limited advantages over self-agent scaling but becomes more effective with increased problem difficulty and decreased model capability, while agent diversity shows little benefit. Conversely, for safety tasks, MAD's collaborative refinement can increase vulnerability, but incorporating diverse agent configurations facilitates a gradual reduction in attack success through the collaborative refinement process. We believe our findings provide critical guidance for the future development of more effective and strategically deployed MAD systems.

cs.AI↗