United States

Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals remain unclear. In this paper, we demonstrate that truthfulness cues arise from two distinct information pathways: (1) a Question-Anchored pathway that depends on question–answer information flow, and (2) an Answer-Anchored pathway that derives self-contained evidence from the generated answer itself. First, we validate and disentangle these pathways through attention knockout and token patching. Afterwards, we uncover notable and intriguing properties of these two mechanisms. Further experiments reveal that (1) the two mechanisms are closely associated with LLM knowledge boundaries; and (2) internal representations are aware of their distinctions. Finally, building on these insightful findings, two applications are proposed to enhance hallucination detection performance. Overall, our work provides new insight into how LLMs internally encode truthfulness, offering directions for more reliable and self-aware generative systems.

ACL 2026

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

technical paper

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Knowledge Tracing (KT) is essential for tracking students’ evolving knowledge states and predicting their future performance. While current graph-based methods focus on exercise-concept relations, they often overlook the inherent group structures among students. Similarly, emerging LLM-based approaches rely on individual histories, lacking the broader context of group references and contrastive evidence. As a result, existing individual-isolation paradigms fail to provide stable predictions and evidence-based explanations. To bridge this gap, we propose Micro-Community Knowledge Tracing (MicroC-KT), a framework that incorporates learning micro-environments to provide social-cognitive anchors for KT. MicroC-KT identifies latent learning communities via hypergraph modeling and generates dual-granular summaries to facilitate community matching and peer retrieval. By extracting contrastive group evidence, the model prompts an LLM to generate both accurate answer predictions and verifiable analysis reports. Experiments on four public datasets demonstrate that MicroC-KT significantly outperforms state-of-the-art baselines in predictive performance while providing more reliable and evidence-based explanations.

MicroC-KT: Modeling Community Effect via Learning Micro-Environment for Evidence-Grounded Explainable Knowledge Tracing

Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.g., output length) to unverifiable ones (e.g., tone). Reinforcement learning with verifiable rewards has emerged as a paradigm for IF tasks, leveraging LLM-as-a-judge to assess unverifiable constraints. However, we empirically find that this approach remains a significant bottleneck, suffering from severe reward hacking and higher computational overhead. In this work, we first analyze the generalization capabilities of unverifiable constraints and discover that specific constraints exhibit distinct, high-generalization patterns. Motivated by this, we propose TinyJudge, a framework that employs an ensemble of specialized tiny language models (e.g., 0.6B) to provide rewards for soft constraints. By distilling expertise from frontier models into these tiny models, it achieves high-precision, lightweight evaluation. Extensive evaluations across five benchmarks demonstrate that TinyJudge outperforms the baselines by ~10% in average performance and 12% in reward precision. Crucially, it also achieves a 3× speedup in total training time. Our work provides a scalable and robust path for aligning LLMs with unverifiable human instructions.

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles

With the surge of online misinformation, Large Language Models (LLMs) and Reasoning Large Language Models (RLMs) serving as Automatic Fact-Checking (AFC) systems have emerged as a prominent paradigm for reliable, explainable verification. However, our empirical study reveals that this paradigm faces a critical risk asymmetry challenge when deployed in real-world under resource-constrained environments. While Hotspot Perception Ability (HPA), the capacity to dynamically allocate reasoning resources based on social impact, is essential to mitigate this risk, existing benchmarks lack the social metadata and evaluation framework to meet this urgent evaluation needs, thereby hindering the advancement of these AFC systems. To bridge this gap, we introduce TrendFact, the first benchmark capable of evaluating HPA and three fact-checking tasks. It consists of 7,643 curated samples sourced from trending platforms and professional datasets, with an evidence library containing 366,634 entries. To enable HPA assessment, we propose two novel metrics: the Explanation Consistency Score (ECS) to evaluate the reliability of verification reasoning, and the Hotspot Claim Perception Index (HCPI) to quantify the overall HPA of AFC systems. Extensive experiments demonstrate that existing AFC systems exhibit limited performance on TrendFact. Furthermore, our proposed FactISR framework effectively enhances HPA and computational efficiency for RLM-driven systems.

TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking

Large language models (LLMs) still struggle with multi-hop reasoning over knowledge-graphs (KGs), and we identify a previously overlooked structural reason for this difficulty: Transformer attention heads naturally specialize in distinct semantic relations across reasoning stages, forming a hop-aligned relay pattern. This key finding suggests that multi-hop reasoning is inherently multi-view, yet existing KG-based retrieval-augmented generation (KG-RAG) systems collapse all reasoning hops into a single representation, flat embedding space, suppressing this implicit structure and causing noisy or drifted path exploration. We introduce ParallaxRAG, a symmetric multi-view framework that decouples queries and KGs into aligned, head-specific retrieval spaces. By enforcing relational diversity across heads while constraining weakly related paths, ParallaxRAG constructs more accurate, cleaner subgraphs and guides LLMs through grounded, hop-wise reasoning. On WebQSP and CWQ, it achieves state-of-the-art retrieval and QA performance, substantially reduces hallucination, and generalizes strongly to the biomedical BioASQ benchmark. Our implementation is available at https://github.com/LucaLiu1313/ParallaxRAG.

Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation

Prefilling computational costs pose a significant bottleneck for Large Language Models (LLMs) and Large Multimodal Models (LMMs) in long-context settings. While token pruning reduces sequence length, prior methods rely on heuristics that break compatibility with hardware-efficient kernels like FlashAttention. In this work, we observe that tokens evolve toward semantic fixing points, making further processing redundant. To this end, we introduce Delta Attention Selective Halting (DASH), a training-free policy that monitors the layer-wise update dynamics of the self-attention mechanism to selectively halt stabilized tokens. Extensive evaluation confirms that DASH generalizes across language and vision benchmarks, delivering significant prefill speedups while preserving model accuracy and hardware efficiency. Code will be released at https://github.com/verach3n/DASH.git .

Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling

Recent progress in Large Language Model (LLM) based Table Question Answering (TableQA) has demonstrated strong performance on standard benchmarks. However, existing benchmarks mainly focus on well-structured tables and fail to reflect the irregular structures and complex reasoning commonly encountered in real-world scenarios. We propose CompTab, a benchmark designed to evaluate TableQA under complex reasoning and irregular table conditions. CompTab covers six representative types, including semantic ambiguity, multi-hop reasoning, transposed tables, merged cells, missing values, and outliers. It is constructed from real-world seed tables across multiple domains using controlled LLM based generation and human verification to ensure realism and diversity. In addition, to improve the generalization of LLMs under complex and irregular table settings, we propose a two-stage training framework that progressively aligns models with textual reasoning and executable decision signals, instantiated as CompTabLLM. Evaluations on 38 representative LLMs and CompTabLLM show clear limitations of existing LLMs under realistic conditions, while the proposed framework improves generalization. CompTab thus provides a challenging benchmark for advancing TableQA in real-world.

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables

High-resolution visual tokens impose substantial computational burdens owing to extreme redundancy in Large Visual Language Models (LVLMs). Existing visual token pruning methods typically leverage simple metrics derived from human experience, such as attention or similarity, to rank and select tokens within a highly entangled feature space. However, these metrics lack interpretability and often introduce human bias, failing to capture the genuine semantic significance of tokens, especially amidst the inherent semantic complexity and ambiguity of visual tokens. To mitigate this limitation, we propose a novel Semantically Comprehensive Token Selection (SCTS) method for unbiased, interpretable visual token pruning via a concept-driven paradigm. To unravel the model’s intrinsic semantic representation mechanism, we first introduce a Sparse Autoencoder to disentangle visual features into an interpretable space, with each dimension encoding a distinct semantic concept. We then formulate the token pruning task as a Maximum Concept Coverage problem, quantifying the Marginal Semantic Gain (MSG) of each token’s contribution to uncovered concepts and iteratively selecting tokens with the highest MSG. This concept-centric approach prioritizes tokens with unique semantic contributions, guaranteeing semantic comprehensiveness while preserving robust performance even at high compression ratios. Extensive experiments across multiple LVLM architectures and benchmarks verify that SCTS consistently outperforms state-of-the-art approaches, achieving a superior trade-off between computational efficiency and semantic completeness.

Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage

While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge this gap but typically rely on inefficient, multi-turn recursive loops that incur high computational costs. To address this, we propose Metacognitive Agent with Reflective Self-improvement (MARS), a framework that achieves efficient self-evolution within a single recurrence cycle. Inspired by educational psychology, MARS mimics human learning by integrating principle-based reflection (abstracting normative rules to avoid errors) and procedural reflection (deriving step-by-step strategies for success). By synthesizing these insights into optimized instructions, MARS allows agents to systematically refine their reasoning logic without continuous online feedback. Extensive experiments on six benchmarks demonstrate that MARS outperforms state-of-the-art self-evolving systems while significantly reducing computational overhead. Code is available at https://github.com/Paparare/MARS/tree/main

Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement

Time plays a critical role in how information is generated, retrieved, and interpreted. In this survey, we provide a comprehensive overview of Temporal Question Answering (TQA), a research area that focuses on answering questions involving temporal constraints or context. As time-stamped content from sources like news articles, web archives, and knowledge bases continues to grow, TQA systems must address challenges such as detecting temporal intent, normalizing time expressions, ordering events, and reasoning over evolving or ambiguous facts. We organize existing work through a unified perspective that captures the interaction between corpus temporality, question temporality, and model capabilities, enabling a systematic comparison of datasets, tasks, and approaches. We review recent advances in TQA enabled by neural architectures, especially transformer-based models and Large Language Models (LLMs), highlighting progress in temporal language modeling, retrieval-augmented generation (RAG), and temporal reasoning. We also discuss benchmark datasets and evaluation strategies designed to test temporal robustness, recency awareness, and generalization.

It's High Time: A Survey of Temporal Question Answering

Evaluating the safety robustness of LLMs is critical for their deployment. However, mainstream Red Teaming methods rely on online generation and black-box output analysis. These approaches are not only costly but also suffer from feedback latency, making them unsuitable for agile diagnostics after training a new model.
To address this, we propose N-GLARE (A Non-Generative, Latent Representation-Efficient LLM Safety Evaluator). N-GLARE operates entirely on the model's latent representations, bypassing the need for full text generation. It characterizes hidden layer dynamics by analyzing the APT (Angular-Probabilistic Trajectory) of latent representations and introducing the JSS (Jensen-Shannon Separability) metric.
Experiments on over 40 models and 20 red teaming strategies demonstrate that the JSS metric exhibits high consistency with Red Teaming safety rankings at less than 1\% token and runtime cost.

Downloads

Next from ACL 2026

MicroC-KT: Modeling Community Effect via Learning Micro-Environment for Evidence-Grounded Explainable Knowledge Tracing

Similar lecture

Truth Knows No Language: Evaluating Truthfulness Beyond English

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2026

MicroC-KT: Modeling Community Effect via Learning Micro-Environment for Evidence-Grounded Explainable Knowledge Tracing

Similar lecture

Truth Knows No Language: Evaluating Truthfulness Beyond English

Downloads