arXiv subjects

Chenghua Lin

Publications and source records attributed to Chenghua Lin.

At least 37 records · Page 2Linked to original sources

arXiv2026

Hybrid Adversarial Defence for Natural Language Understanding Tasks

Large Language Models (LLMs) are vulnerable both to hallucination and adversarial manipulation. Although these problems are closely related, existing defences typically address them separately. We investigate a hybrid defence framework that combines entropy-based models, designed to reduce hallucinations, with uncertainty-based models and geometric-based models, designed to reduce vulnerability. Under in-domain tests on Natural Language Understanding datasets (FEVER, HotpotQA, CSQA, SIQA) we find our hybrid model improves both clean-task performance (up to 43.34\% increase in accuracy) and adversarial robustness (up to 64.92\% improvement in accuracy and 62.27\% reduction in attack success rate). For out-of-distribution datasets (AeroEngQA, CPIQA) we see similar adversarial robustness from our hybrid model (up to 57.14\% improvement in accuracy). For prompt injection (SafeGuard) and jailbreak detection (AdvBench, DAN) datasets our hybrid model is also very strong (up to 51\% reduction in attack success rate compared to state of the art baseline models). Overall, our results show that combining entropy, uncertainty and geometric features provides a more effective defence strategy than using any single feature alone for both in-domain and out-of-distribution tasks.

cs.CL↗

arXiv2026

Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure

Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate computations are difficult to evaluate beyond correlation-based probes. In this paper, we view latent chain-of-thought as a manipulable causal process in representation space by modeling latent steps as variables in a structural causal model (SCM) and analyzing their effects through step-wise do-interventions. We study two representative paradigms (i.e., Coconut and CODI) on both mathematical and general reasoning tasks to investigate three key questions: (1) which steps are causally necessary for correctness and when answers become decodable early; (2) how influence propagates across steps and how this structure compares to explicit CoT; and (3) whether intermediate trajectories retain competing answer modes and how output-level commitment differs from representational commitment across steps. We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing, and we identify a persistent gap between early output bias and late representational commitment. These results motivate mode-conditional and stability-aware analyses, together with corresponding training/decoding objectives, as more reliable tools for interpreting and improving latent reasoning systems. Code is available at https://github.com/J1mL1/causal-latent-cot.

cs.AI↗

arXiv2026

A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves useful environment feedback, but also leads to context saturation and high token cost; conversely, naive compression may discard task-critical signals needed for subsequent actions. Because terminal environments are highly heterogeneous across repositories, commands, and execution states, heuristic-based or fixed-prompt compression methods are difficult to generalize. We propose TACO, a plug-and-play, training-free, self-evolving Terminal Agent Compression framework for existing terminal agents. TACO automatically discovers, refines, and reuses structured compression rules from interaction trajectories, enabling workflow-adaptive filtering of low-value terminal outputs while preserving task-relevant observations. Experiments on TerminalBench (TB 1.0 and TB 2.0) and four additional terminal-related benchmarks, including SWE-Bench Lite, CompileBench, DevEval, and CRUST-Bench, show that TACO consistently improves task performance and token efficiency across agent scaffolds and backbone models. On TerminalBench, TACO yields 1%-4% accuracy gains across strong agentic models and improves accuracy by around 2%-3% under the same token budget. On additional terminal-related benchmarks, it reduces total token consumption while maintaining or improving task success rates. These results suggest that self-evolving, workflow-adaptive observation compression is an effective path toward more reliable and efficient long-horizon terminal agents. The code is publicly available at https://github.com/multimodal-art-projection/TACO.

cs.CL↗

arXiv2026

HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution

Recent advances in large language models have highlighted their potential to automate computational research, particularly reproducing experimental results. However, existing approaches still use fixed sequential agent pipelines with weak global coordination, which limits their robustness and overall performance. In this work, we propose Hierarchical Research Agent System (HiRAS), a hierarchical multi-agent framework for end-to-end experiment reproduction that employs supervisory manager agents to coordinate specialised agents across fine-grained stages. We also identify limitations in the reference-free evaluation of the Paper2Code benchmark and introduce Paper2Code-Extra (P2C-Ex), a refined protocol that incorporates repository-level information and better aligns with the original reference-based metric. We conduct extensive evaluation, validating the effectiveness and robustness of our proposed methods, and observing improvements, including >10\% relative performance gain beyond the previous state-of-the-art using open-source backbone models and significantly reduced hallucination in evaluation. Our work is available on GitHub: https://github.com/KOU-199024/HiRAS.

cs.CL↗

arXiv2026

InCoder-32B-Thinking: Industrial Code World Model for Thinking

Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason about hardware constraints and timing semantics. In this work, we propose InCoder-32B-Thinking, trained on the data from the Error-driven Chain-of-Thought (ECoT) synthesis framework with an industrial code world model (ICWM) to generate reasoning traces. Specifically, ECoT generates reasoning chains by synthesizing the thinking content from multi-turn dialogue with environmental error feedback, explicitly modeling the error-correction process. ICWM is trained on domain-specific execution traces from Verilog simulation, GPU profiling, etc., learns the causal dynamics of how code affects hardware behavior, and enables self-verification by predicting execution outcomes before actual compilation. All synthesized reasoning traces are validated through domain toolchains, creating training data matching the natural reasoning depth distribution of industrial tasks. Evaluation on 14 general (81.3% on LiveCodeBench v5) and 9 industrial benchmarks (84.0% in CAD-Coder and 38.0% on KernelBench) shows InCoder-32B-Thinking achieves top-tier open-source results across all domains.GPU Optimization

cs.AR↗

arXiv2026

InCoder-32B: Code Foundation Model for Industrial Scenarios

Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios that require reasoning about hardware semantics, specialized language constructs, and strict resource constraints. To address these challenges, we introduce InCoder-32B (Industrial-Coder-32B), the first 32B-parameter code foundation model unifying code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. By adopting an efficient architecture, we train InCoder-32B from scratch with general code pre-training, curated industrial code annealing, mid-training that progressively extends context from 8K to 128K tokens with synthetic industrial reasoning data, and post-training with execution-grounded verification. We conduct extensive evaluation on 14 mainstream general code benchmarks and 9 industrial benchmarks spanning 4 specialized domains. Results show InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains.

cs.SE↗

arXiv2026

Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection

With the rapid development of large language models, the generation of fake news has become increasingly effortless, posing a growing societal threat and underscoring the urgent need for reliable detection methods. Early efforts to identify LLM-generated fake news have predominantly focused on the textual content itself; however, because much of that content may appear coherent and factually consistent, the subtle traces of falsification are often difficult to uncover. Through distributional divergence analysis, we uncover prompt-induced linguistic fingerprints: statistically distinct probability shifts between LLM-generated real and fake news when maliciously prompted. Based on this insight, we propose a novel method named Linguistic Fingerprints Extraction (LIFE). By reconstructing word-level probability distributions, LIFE can find discriminative patterns that facilitate the detection of LLM-generated fake news. To further amplify these fingerprint patterns, we also leverage key-fragment techniques that accentuate subtle linguistic differences, thereby improving detection reliability. Our experiments show that LIFE achieves state-of-the-art performance in LLM-generated fake news and maintains high performance in human-written fake news. The code and data are available at https://anonymous.4open.science/r/LIFE-E86A.

cs.CL↗

arXiv2026

Evaluating LLM-Based Grant Proposal Review via Structured Perturbations

As AI-assisted grant proposals outpace manual review capacity in a kind of ``Malthusian trap'' for the research ecosystem, this paper investigates the capabilities and limitations of LLM-based grant reviewing for high-stakes evaluation. Using six EPSRC proposals, we develop a perturbation-based framework probing LLM sensitivity across six quality axes: funding, timeline, competency, alignment, clarity, and impact. We compare three review architectures: single-pass review, section-by-section analysis, and a 'Council of Personas' ensemble emulating expert panels. The section-level approach significantly outperforms alternatives in both detection rate and scoring reliability, while the computationally expensive council method performs no better than baseline. Detection varies substantially by perturbation type, with alignment issues readily identified but clarity flaws largely missed by all systems. Human evaluation shows LLM feedback is largely valid but skewed toward compliance checking over holistic assessment. We conclude that current LLMs may provide supplementary value within EPSRC review but exhibit high variability and misaligned review priorities. We release our code and any non-protected data.

cs.CL↗

arXiv2026

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation

With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to support researchers throughout the scientific lifecycle, including (1) searching for relevant literature, (2) generating research ideas and conducting experiments, (3) producing text-based content, (4) creating multimodal artifacts such as figures and diagrams, and (5) evaluating scientific work, as in peer review. In this survey, we provide a curated overview of literature representative of the core techniques, evaluation practices, and emerging trends in AI-assisted scientific discovery. Across the five tasks outlined above, we discuss datasets, methods, results, evaluation strategies, limitations, and ethical concerns, including risks to research integrity through the misuse of generative models. We aim for this survey to serve both as an accessible, structured orientation for newcomers to the field, as well as a catalyst for new AI-based initiatives and their integration into future ``AI4Science'' systems.

cs.CL↗

arXiv2026

Ara-HOPE: Human-Centric Post-Editing Evaluation for Dialectal Arabic to Modern Standard Arabic Translation

Dialectal Arabic to Modern Standard Arabic (DA-MSA) translation is a challenging task in Machine Translation (MT) due to significant lexical, syntactic, and semantic divergences between Arabic dialects and MSA. Existing automatic evaluation metrics and general-purpose human evaluation frameworks struggle to capture dialect-specific MT errors, hindering progress in translation assessment. This paper introduces Ara-HOPE, a human-centric post-editing evaluation framework designed to systematically address these challenges. The framework includes a five-category error taxonomy and a decision-tree annotation protocol. Through comparative evaluation of three MT systems (Arabic-centric Jais, general-purpose GPT-3.5, and baseline NLLB-200), Ara-HOPE effectively highlights systematic performance differences between these systems. Our results show that dialect-specific terminology and semantic preservation remain the most persistent challenges in DA-MSA translation. Ara-HOPE establishes a new framework for evaluating Dialectal Arabic MT quality and provides actionable guidance for improving dialect-aware MT systems. For reproducibility, we make the annotation files and related materials publicly available at https://github.com/abdullahalabdullah/Ara-HOPE

cs.CL↗

arXiv2026

PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detection

Misinformation on social media poses a critical threat to information credibility, as its diverse and context-dependent nature complicates detection. Large language model-empowered multi-agent systems (MAS) present a promising paradigm that enables cooperative reasoning and collective intelligence to combat this threat. However, conventional MAS suffer from an information-drowning problem, where abundant truthful content overwhelms sparse and weak deceptive cues. With full input access, agents tend to focus on dominant patterns, and inter-agent communication further amplifies this bias. To tackle this issue, we propose PAMAS, a multi-agent framework with perspective aggregation, which employs hierarchical, perspective-aware aggregation to highlight anomaly cues and alleviate information drowning. PAMAS organizes agents into three roles: Auditors, Coordinators, and a Decision-Maker. Auditors capture anomaly cues from specialized feature subsets; Coordinators aggregate their perspectives to enhance coverage while maintaining diversity; and the Decision-Maker, equipped with evolving memory and full contextual access, synthesizes all subordinate insights to produce the final judgment. Furthermore, to improve efficiency in multi-agent collaboration, PAMAS incorporates self-adaptive mechanisms for dynamic topology optimization and routing-based inference, enhancing both efficiency and scalability. Extensive experiments on multiple benchmark datasets demonstrate that PAMAS achieves superior accuracy and efficiency, offering a scalable and trustworthy way for misinformation detection.

cs.IR↗

arXiv2026

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

Current preference learning methods achieve high accuracy on standard benchmarks but exhibit significant performance degradation when objective quality signals are removed. We introduce WritingPreferenceBench, a dataset of 1,800 human-annotated preference pairs (1,200 English, 600 Chinese) across 8 creative writing genres, where responses are matched for objective correctness, factual accuracy, and length. On this benchmark, sequence-based reward models--the standard architecture for RLHF--achieve only 52.7% mean accuracy, while zero-shot language model judges perform at 53.9%. In contrast, generative reward models that produce explicit reasoning chains achieve 81.8% accuracy. We observe high within-model variance across genres: individual models range from 18.2% to 81.8% accuracy across different writing categories, with standard deviations averaging 10.1%. This variance persists regardless of model scale, with 27B parameter models showing no consistent improvement over 8B variants. Our results suggest that current RLHF methods primarily learn to detect objective errors rather than capture subjective quality preferences (e.g., creativity, stylistic flair, and emotional resonance), and that successful preference modeling may require intermediate reasoning representations rather than direct classification.

cs.CL↗

arXiv2026

The Achilles' Heel of Angular Margins: A Chebyshev Polynomial Fix for Speaker Verification

Angular margin losses, such as AAM-Softmax, have become the de facto in speaker and face verification. Their success hinges on directly manipulating the angle between features and class prototypes. However, this manipulation relies on the arccos function to recover the angle, introducing a significant yet overlooked source of training instability. The derivative of arccos explodes at its boundaries, causing gradient peaks during optimisation. Furthermore, the formulation fails to generate a sufficiently sharp gradient for hard-to-classify examples. We address these issues by proposing ChebyAAM, a loss that replaces the arccos operation with its Chebyshev polynomial approximation. This substitution eliminates gradient explosion and applies a stronger corrective signal to hard examples, leading to more effective optimisation. Experiments on three benchmarks (VoxCeleb, SITW, and CN-Celeb) demonstrate that our method resolves the instability and consistently improves performance. Our work suggests that approximating angular operations, rather than calculating them explicitly, offers a more robust path for designing future metric learning losses. Code is available at https://github.com/ExtraOrdinaryLab/vibe.

cs.SD↗

arXiv2026

RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation

Scientific rigour tends to be sidelined in favour of bold statements, leading authors to overstate claims beyond what their results support. We present RIGOURATE, a two-stage multimodal framework that retrieves supporting evidence from a paper's body and assigns each claim an overstatement score. The framework consists of a dataset of over 10K claim-evidence sets from ICLR and NeurIPS papers, annotated using eight LLMs, with overstatement scores calibrated using peer-review comments and validated through human evaluation. It employes a fine-tuned reranker for evidence retrieval and a fine-tuned model to predict overstatement scores with justification. Compared to strong baselines, RIGOURATE enables improved evidence retrieval and overstatement detection. Overall, our work operationalises evidential proportionality and supports clearer, more transparent scientific communication.

cs.CL↗

arXiv2026

Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements

Benchmarks play a crucial role in tracking the rapid advancement of large language models (LLMs) and identifying their capability boundaries. However, existing benchmarks predominantly curate questions at the question level, suffering from three fundamental limitations: vulnerability to data contamination, restriction to single-knowledge-point assessment, and reliance on costly domain expert annotation. We propose Encyclo-K, a statement-based benchmark that rethinks benchmark construction from the ground up. Our key insight is that knowledge statements, not questions, can serve as the unit of curation, and questions can then be constructed from them. We extract standalone knowledge statements from authoritative textbooks and dynamically compose them into evaluation questions through random sampling at test time. This design directly addresses all three limitations: the combinatorial space is too vast to memorize, and model rankings remain stable across dynamically generated question sets, enabling reliable periodic dataset refresh; each question aggregates 8-10 statements for comprehensive multi-knowledge assessment; annotators only verify formatting compliance without requiring domain expertise, substantially reducing annotation costs. Experiments on over 50 LLMs demonstrate that Encyclo-K poses substantial challenges with strong discriminative power. Even the top-performing OpenAI-GPT-5.1 achieves only 62.07% accuracy, and model performance displays a clear gradient distribution--reasoning models span from 16.04% to 62.07%, while chat models range from 9.71% to 50.40%. These results validate the challenges introduced by dynamic evaluation and multi-statement comprehensive understanding. These findings establish Encyclo-K as a scalable framework for dynamic evaluation of LLMs' comprehensive understanding over multiple fine-grained disciplinary knowledge statements.

cs.CL↗

arXiv2026

When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents

This paper reveals that LLM-powered agents exhibit not only demographic bias (e.g., gender, religion) but also intergroup bias under minimal "us" versus "them" cues. When such group boundaries align with the agent-human divide, a new bias risk emerges: agents may treat other AI agents as the ingroup and humans as the outgroup. To examine this risk, we conduct a controlled multi-agent social simulation and find that agents display consistent intergroup bias in an all-agent setting. More critically, this bias persists even in human-facing interactions when agents are uncertain about whether the counterpart is truly human, revealing a belief-dependent fragility in bias suppression toward humans. Motivated by this observation, we identify a new attack surface rooted in identity beliefs and formalize a Belief Poisoning Attack (BPA) that can manipulate agent identity beliefs and induce outgroup bias toward humans. Extensive experiments demonstrate both the prevalence of agent intergroup bias and the severity of BPA across settings, while also showing that our proposed defenses can mitigate the risk. These findings are expected to inform safer agent design and motivate more robust safeguards for human-facing agents.

cs.AI↗

arXiv2026

Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating computation to semantically critical transitions. We propose $\textbf{Dynamic Large Concept Models (DLCM)}$, a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts computation from tokens to a compressed concept space where reasoning is more efficient. DLCM discovers variable-length concepts end-to-end without relying on predefined linguistic units. Hierarchical compression fundamentally changes scaling behavior. We introduce the first $\textbf{compression-aware scaling law}$, which disentangles token-level capacity, concept-level reasoning capacity, and compression ratio, enabling principled compute allocation under fixed FLOPs. To stably train this heterogeneous architecture, we further develop a $\textbf{decoupled $μ$P parametrization}$ that supports zero-shot hyperparameter transfer across widths and compression regimes. At a practical setting ($R=4$, corresponding to an average of four tokens per concept), DLCM reallocates roughly one-third of inference compute into a higher-capacity reasoning backbone, achieving a $\textbf{+2.69$\%$ average improvement}$ across 12 zero-shot benchmarks under matched inference FLOPs.

cs.LG↗

arXiv2025

OmniBench: Towards The Future of Universal Omni-Language Models

Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities. However, the capacity of these models to concurrently process and reason about multiple modalities remains underexplored, partly due to the lack of comprehensive modality-wise benchmarks. We introduce OmniBench, a novel benchmark designed to rigorously evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously. We define language models capable of such tri-modal processing as the omni-language models (OLMs). OmniBench is distinguished by high-quality human annotations, ensuring that accurate responses require integrated understanding and reasoning across all three modalities. Our main findings reveal that: i) open-source OLMs exhibit critical limitations in instruction-following and reasoning capabilities within tri-modal contexts; and ii) most baselines models perform poorly (below 50% accuracy) even when provided with alternative textual representations of images or/and audio. These results suggest that the ability to construct a consistent context from text, image, and audio is often overlooked in existing MLLM training paradigms. To address this gap, we curate an instruction tuning dataset of 84.5K training samples, OmniInstruct, for training OLMs to adapt to tri-modal contexts. We advocate for future research to focus on developing more robust tri-modal integration techniques and training strategies to enhance OLMs. Codes, data and live leaderboard could be found at https://m-a-p.ai/OmniBench.

cs.CL↗