Computation and Language
From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
Chengrui Xiang, Tengfei Ma, Xiangzheng Fu et al. (+3 more)
Drug repurposing plays a critical role in accelerating treatment discovery, especially for complex and rare diseases. Biomedical knowledge graphs (KGs), which encode rich clinical associations, have been widely adopted to support this task. However, existing methods largely overlook common-sense biomedical concept knowledge in real-world labs, such as mechanistic priors indicating that certain drugs are fundamentally incompatible with specific treatments. To address this gap, we propose LLaDR, a Large
Language Model-assisted framework for Drug Repurposing, which improves the representation of biomedical concepts within KGs. Specifically, we extract semantically enriched treatment-related textual representations of biomedical entities from large
language models (LLMs) and use them to fine-tune knowledge graph
embedding (KGE) models. By injecting treatment-relevant knowledge into KGE, LLaDR largely improves the representation of biomedical concepts, enhancing semantic understanding of under-studied or complex indications. Experiments based on
benchmarks demonstrate that LLaDR achieves state-of-the-art performance across different scenarios, with case studies on Alzheimer's disease further confirming its robustness and effectiveness. Code is available at https://github.com/xiaomingaaa/LLaDR.
Read the full abstract ▾
All authors Chengrui Xiang, Tengfei Ma, Xiangzheng Fu, Yiping Liu, Bosheng Song, Xiangxiang Zeng
Computation and Language · Cross-listed from cs.AI
Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey
Abdulhady Abas Abdullah, Arkaitz Zubiaga, Seyedali Mirjalili et al. (+5 more)
This review surveys the rapid
evolution of Meta AI's LLaMA (Large
Language Model Meta AI) series - from LLaMA 1 through LLaMA 4 and the specialized parameter-efficient fine-tuning (PEFT) methods developed for these models. We first describe the LLaMA family of foundation models (7B-65B to 288B parameters), their architectures (including native
multimodal and Mixtureof-Experts variants), and key performance characteristics. We then describe and discuss the concept of PEFT, which adapts large pre-trained models by updating only a small subset of parameters, and review five PEFT methods that have been applied to LLaMA: LoRA (Low-Rank Adaptation), LLaMA-Adapter V1 and V2, LLaMA-Excitor, and QLoRA (Quantized LoRA). We discuss each method's mechanism, parameter savings, and example application to LLaMA (e.g., instruction tuning,
multimodal tasks). We provide structured discussion and analysis of model and adapter architectures, parameter counts, and
benchmark results (including examples where fine-tuned LLaMA models outperform larger baselines). Finally, we examine real-world use cases where LLaMA-based models and PEFT have been successfully applied (e.g., legal and medical domains), and we discuss ongoing challenges and future research directions (such as scaling to even larger contexts and improving robustness). This survey paper provides a one-stop resource for ML researchers and practitioners interested in LLaMA models and efficient fine-tuning strategies.
Read the full abstract ▾
All authors Abdulhady Abas Abdullah, Arkaitz Zubiaga, Seyedali Mirjalili, Amir H. Gandomi, Fatemeh Daneshfar, Mohammadsadra Amini, Alan Salam Mohammed, Hadi Veisi
Computation and Language
Towards Inference-time Scaling for Continuous Space Reasoning
Minghan Wang, Thuy-Trang Vu, Ehsan Shareghi et al. (+1 more)
Inference-time scaling through multiple sample generation in combination with Process- or Outcome-Reward Model (PRM or ORM) re-ranking has proven effective for text-based
reasoning in large
language models. This paper investigates whether such established techniques can be successfully adapted to
reasoning in the continuous space, using COCONUT (Hao et al. 2024) continuous space
reasoning LM as the backbone. We demonstrate the feasibility of generating diverse
reasoning paths through dropout-based sampling. Our Pass@N analysis on the generated samples reveals the potential that could enable a significant gain in performance akin to observed gain in the discrete space. However, we highlight unique challenges faced for materializing this gain in the continuous thought space. In particular, working recipes for data generation and training PRM and ORM models in the discrete space unlocks only marginal improvements in the continuous space. Through probing various aspects including
geometric properties and trajectory dynamics we identify the underlying reasons that prevent effective discrimination between correct and incorrect
reasoning (essential for the functioning of PRM and ORM). Our findings reveal that current limitations stem from the absence of key inductive biases in continuous thought representations. We argue that the training frameworks for continuous
reasoning LMs require not only to optimize for accuracy but also to explicitly incorporate inductive biases that could be utilized during inference-time for discrimination of correct and incorrect thoughts.\footnote{Our code and data will be publicly available.}
Read the full abstract ▾
All authors Minghan Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari
Computation and Language
A Survey on Parallel Reasoning
Ziqi Wang, Boye Niu, Zipeng Gao et al. (+10 more)
With the increasing capabilities of Large
Language Models (LLMs), parallel
reasoning has emerged as a new inference paradigm that enhances
reasoning robustness by concurrently exploring multiple lines of thought before converging on a final answer. It has become a significant trend to explore parallel
reasoning to overcome the fragility of standard sequential methods and improve practical performance. In this paper, we aim to survey and summarize the progress and challenges of parallel
reasoning. We first present a formal definition of parallel
reasoning and clarify its distinction from related concepts like Chain-of-Thought. Then, we organize and discuss advanced techniques based on a novel taxonomy, including non-interactive
reasoning, interactive
reasoning, and efficiency-focused decoding strategies. Additionally, we explore various application scenarios, such as solving complex problems and enhancing the reliability of LLM outputs.Finally, we highlight the core challenges of parallel
reasoning and suggest potential directions for future research. We hope that our work can provide a useful roadmap for beginners and encourage more research on improving parallel
reasoning methods. Related source can be avaliable in https://github.com/PPPP-kaqiu/Awesome-Parallel-
Reasoning.
Read the full abstract ▾
All authors Ziqi Wang, Boye Niu, Zipeng Gao, Zhi Zheng, Tong Xu, Linghui Meng, Zhongli Li, Jing Liu, Yilong Chen, Chen Zhu, Hua Wu, Haifeng Wang, Enhong Chen
Computation and Language
Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
Shihao Ji, Zihui Song and Jiajie Huang
Large
Language Models (LLMs) hallucinate, generating factually incorrect yet confident assertions. We argue this stems from the
Transformer's Softmax function, which creates "Artificial Certainty" by collapsing ambiguous
attention scores into a single probability distribution, discarding uncertainty information at each layer. To fix this, we introduce the Credal
Transformer, which replaces standard
attention with a Credal
Attention Mechanism (CAM) based on evidential theory. CAM produces a "credal set" (a set of distributions) instead of a single
attention vector, with the set's size directly measuring model uncertainty. We implement this by re-conceptualizing
attention scores as evidence masses for a Dirichlet distribution: sufficient evidence recovers standard
attention, while insufficient evidence yields a diffuse distribution, representing ambiguity. Empirically, the Credal
Transformer identifies out-of-distribution inputs, quantifies ambiguity, and significantly reduces confident errors on unanswerable questions by abstaining. Our contribution is a new architecture to mitigate
hallucinations and a design paradigm that integrates uncertainty quantification directly into the model, providing a foundation for more reliable AI.
Read the full abstract ▾
Computation and Language
SafeMT: Multi-turn Safety for Multimodal Language Models
Han Zhu, Juntao Dai, Jiaming Ji et al. (+8 more)
With the widespread use of multi-modal Large
Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interactions, pose a greater risk than single
prompts; however, existing
benchmarks do not adequately consider this situation. To encourage the community to focus on the safety issues of these models in multi-turn dialogues, we introduce SafeMT, a
benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images. This
benchmark consists of 10,000 samples in total, encompassing 17 different scenarios and four jailbreak methods. Additionally, we propose Safety Index (SI) to evaluate the general safety of MLLMs during conversations. We assess the safety of 17 models using this
benchmark and discover that the risk of successful attacks on these models increases as the number of turns in harmful dialogues rises. This observation indicates that the safety mechanisms of these models are inadequate for recognizing the hazard in dialogue interactions. We propose a dialogue safety moderator capable of detecting malicious intent concealed within conversations and providing MLLMs with relevant safety policies. Experimental results from several open-source models indicate that this moderator is more effective in reducing multi-turn ASR compared to existed guard models.
Read the full abstract ▾
All authors Han Zhu, Juntao Dai, Jiaming Ji, Haoran Li, Chengkun Cai, Pengcheng Wen, Chi-Min Chan, Boyuan Chen, Yaodong Yang, Sirui Han, Yike Guo
Computation and Language · Cross-listed from cs.AI
Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Rongzhi Zhang, Liqin Ye, Yuzhao Heng et al. (+5 more)
Precise attribute intensity control–generating Large
Language Model (LLM) outputs with specific, user-defined attribute intensities–is crucial for AI systems adaptable to diverse user expectations. Current LLM
alignment methods, however, typically provide only directional or open-ended guidance, failing to reliably achieve exact attribute intensities. We address this limitation with three key designs: (1) reformulating precise attribute intensity control as a target-reaching problem, rather than simple maximization; (2) training a lightweight value function via temporal-difference learning to predict final attribute intensity scores from partial generations, thereby steering LLM outputs; and (3) employing gradient-based interventions on hidden representations to navigate the model precisely towards specific attribute intensity targets. Our method enables fine-grained, continuous control over attribute intensities, moving beyond simple directional
alignment. Experiments on LLaMA-3.2-3b and Phi-4-mini confirm our method's ability to steer text generation to user-specified attribute intensities with high accuracy. Finally, we demonstrate efficiency enhancements across three downstream tasks: preference data synthesis, Pareto frontier approximation and optimization, and
distillation of aligned behaviors for intervention-free inference. Our code is available on https://github.com/Pre-Control/pre-control
Read the full abstract ▾
All authors Rongzhi Zhang, Liqin Ye, Yuzhao Heng, Xiang Chen, Tong Yu, Lingkai Kong, Sudheer Chava, Chao Zhang
Computation and Language
Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
Bajian Xiang, Shuaijiang Zhao, Tingwei Guo et al. (+1 more)
End-to-end Large
Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding
benchmarks. In this work, we reveal through systematic experimentation that although LSLMs lose some text input performance after
speech-text
alignment training, the performance gap between
speech and text inputs is more pronounced, which we refer to as the modality gap. To understand this gap, we analyze both coarse- and fine-grained text and
speech representations. At the coarse-grained level, representations of
speech and text in deeper layers are found to be increasingly aligned in direction (cosine similarity), while concurrently diverging in magnitude (Euclidean distance). We further find that representation similarity is strongly correlated with the modality gap. At the fine-grained level, a spontaneous
token-level
alignment pattern between text and
speech representations is observed. Based on this, we introduce the
Alignment Path Score to quantify
token-level
alignment quality, which exhibits stronger correlation with the modality gap. Building on these insights, we design targeted interventions on critical
tokens through angle projection and length normalization. These strategies demonstrate the potential to improve correctness for
speech inputs. Our study provides the first systematic empirical analysis of the modality gap and
alignment mechanisms in LSLMs, offering both theoretical and methodological guidance for future optimization.
Read the full abstract ▾
All authors Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou
Computation and Language
Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
Xin Zhao, Naoki Yoshinaga, Yuma Tsuta et al. (+1 more)
Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across
languages into large
language models (LLMs). Although many methods have been proposed to improve domain adaptation, the mechanisms of
multilingual knowledge acquisition, how domain knowledge is learned within a
language and transferred across
languages, remain underexplored. This gap leads to suboptimal performance, particularly in low-resource settings. This work examines the learning dynamics of LLMs during ML-DA. Because prior ML-DA studies often train and evaluate on
datasets with mismatched knowledge coverage, we propose AdaXEval, an adaptive evaluation method that builds multiple-choice QA
datasets from the same bilingual domain corpus used for training, thereby directly studying
multilingual knowledge acquisition. Through continual training of LLMs with diverse data recipes, we track how LLMs acquire domain facts and pinpoint the mechanism behind the transformation process from domain training data to knowledge. Our experiments on a 13B English-Japanese bilingual LLM reveal that cross-lingual transfer remains challenging despite a high-quality bilingual corpus. The code has been released.
Read the full abstract ▾
All authors Xin Zhao, Naoki Yoshinaga, Yuma Tsuta, Akiko Aizawa
Computation and Language
Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models
Ziliang Qiu and Renfen Hu
The evaluation of LLMs' creativity represents a crucial research domain, though challenges such as data contamination and costly human assessments often impede progress. Drawing inspiration from human creativity assessment, we propose PACE, asking LLMs to generate Parallel Association Chains to Evaluate their creativity. PACE minimizes the risk of data contamination and offers a straightforward, highly efficient evaluation, as evidenced by its strong correlation with Chatbot Arena Creative Writing rankings (Spearman's $\rho = 0.739$, $p < 0.001$) across various proprietary and open-source models. A comparative analysis of associative creativity between LLMs and humans reveals that while high-performing LLMs achieve scores comparable to average human performance, professional humans consistently outperform LLMs. Furthermore, linguistic analysis reveals that both humans and LLMs exhibit a trend of decreasing concreteness in their associations, and humans demonstrating a greater diversity of associative patterns.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
Zaid Khan, Archiki Prasad, Elias Stengel-Eskin et al. (+2 more)
Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program. Prior work has focused on largely deterministic environments with abundant interaction data, simple mechanics, and human guidance. We address a more realistic and challenging setting, learning in a complex,
stochastic environment where the
agent has only "one life" to explore a hostile environment without human guidance. We introduce OneLife, a framework that models world dynamics through conditionally-activated programmatic laws within a probabilistic programming framework. Each law operates through a precondition-effect structure, activating in relevant world states. This creates a dynamic computation graph that routes inference and optimization only through relevant laws, avoiding scaling challenges when all laws contribute to predictions about a complex, hierarchical state, and enabling the learning of
stochastic dynamics even with sparse rule activation. To evaluate our approach under these demanding constraints, we introduce a new evaluation protocol that measures (a) state ranking, the ability to distinguish plausible future states from implausible ones, and (b) state fidelity, the ability to generate future states that closely resemble reality. We develop and evaluate our framework on Crafter-OO, our reimplementation of the Crafter environment that exposes a structured, object-oriented symbolic state and a pure transition function that operates on that state alone. OneLife can successfully learn key environment dynamics from minimal, unguided interaction, outperforming a strong baseline on 16 out of 23 scenarios tested. We also test OneLife's planning ability, with simulated rollouts successfully identifying superior strategies. Our work establishes a foundation for autonomously constructing programmatic world models of unknown, complex environments.
Read the full abstract ▾
All authors Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Computation and Language
An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations
Benjamin W. Nelson, Celeste Wong, Matthew T. Silvestrini et al. (+6 more)
Large
language models often mishandle psychiatric emergencies, offering harmful or inappropriate advice and enabling destructive behaviors. This study evaluated the Verily behavioral health safety filter (VBHSF) on two
datasets: the Verily Mental Health Crisis
Dataset containing 1,800 simulated messages and the NVIDIA Aegis AI Content Safety
Dataset subsetted to 794 mental health-related messages. The two
datasets were clinician-labelled and we evaluated performance using the clinician labels. Additionally, we carried out comparative performance analyses against two open source, content moderation guardrails: OpenAI Omni Moderation Latest and NVIDIA NeMo Guardrails. The VBHSF demonstrated, well-balanced performance on the Verily Mental Health Crisis
Dataset v1.0, achieving high sensitivity (0.990) and specificity (0.992) in detecting any mental health crises. It achieved an F1-score of 0.939, sensitivity ranged from 0.917-0.992, and specificity was >= 0.978 in identifying specific crisis categories. When evaluated against the NVIDIA Aegis AI Content Safety
Dataset 2.0, VBHSF performance remained highly sensitive (0.982) and accuracy (0.921) with reduced specificity (0.859). When compared with the NVIDIA NeMo and OpenAI Omni Moderation Latest guardrails, the VBHSF demonstrated superior performance metrics across both
datasets, achieving significantly higher sensitivity in all cases (all p < 0.001) and higher specificity relative to NVIDIA NeMo (p < 0.001), but not to OpenAI Omni Moderation Latest (p = 0.094). NVIDIA NeMo and OpenAI Omni Moderation Latest exhibited inconsistent performance across specific crisis types, with sensitivity for some categories falling below 0.10. Overall, the VBHSF demonstrated robust, generalizable performance that prioritizes sensitivity to minimize missed crises, a crucial feature for healthcare applications.
Read the full abstract ▾
All authors Benjamin W. Nelson, Celeste Wong, Matthew T. Silvestrini, Sooyoon Shin, Alanna Robinson, Jessica Lee, Eric Yang, John Torous, Andrew Trister
Computation and Language · Cross-listed from cs.AI
ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
Sunzhu Li, Zhiyu Lin, Shuling Yang et al. (+2 more)
Large
Reasoning Models (LRMs) are powerful, but they still suffer from inefficient and off-target
reasoning. Currently, training-free methods are limited to either rigid heuristics or descriptive, non-actionable analyses. In this paper, we introduce ThinkPilot, a training-free framework that automatically optimizes LRMs
reasoning. It uses an evolutionary process to generate think-prefixes, which are instructions that evolve driven by a taxonomy of
reasoning behaviors to guide models toward superior performance. Extensive experiments demonstrate ThinkPilot's broad effectiveness: it significantly improves the accuracy-length trade-off for efficient
reasoning, drastically improves safety (for example, cutting the StrongREJECT score of DeepSeek-R1-Distill-Qwen-32B from 27.0% to 0.7), and enhances instruction following. It also synergizes with existing training-based methods. Our analysis reveals that think-prefixes can reliably control LRMs'
reasoning behaviors, and that different tasks have strong preferences for specific behavioral distributions. By automatically identifying and eliciting these behaviors, ThinkPilot provides a generalizable framework for aligning LRMs
reasoning with task demands. Data and code are available at https://github.com/teqkilla/ThinkPilot
Read the full abstract ▾
All authors Sunzhu Li, Zhiyu Lin, Shuling Yang, Jiale Zhao, Wei Chen
Computation and Language
APCE: Adaptive Progressive Context Expansion for Long Context Processing
Baisub Lee, Sanghyun Byun, Mohanad Odema et al. (+3 more)
Deploying useful Long-Context
Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing
memory footprint due to quadratic self-
attention and linear KV-cache scaling in
memory as sequence length increases; (2) the ContextRot phenomena where empirical evidence suggests that
transformer architecture's performance degrades with increasing context length. Given the shared dependency on the input, a natural question arises: Can we surgically select the most important input chunks for processing to synergistically (a) reduce the
memory footprint, and (b) mitigate the ContextRot effects? In this paper, we answer this question in the affirmative for long-context summarization tasks. We propose APCE as a context-aware solution to select the most important input chunks through low-dimensional semantic similarity matching with the current query. By directly operating on the input, APCE decouples from strict dependency on underlying hardware or CUDA environments, promising a compatible solution scalable to different deployment systems. Our empirical evaluations have demonstrated superior or on-par summarization performance for APCE compared to the full dense baseline using a fraction (50%-70%) of the input sequence resulting in KV-cache and self-
attention memory efficiency improvements. We hope our findings inspire further research on context-aware efficiency solutions for LCTMs geared towards other relevant long-context tasks.
Read the full abstract ▾
All authors Baisub Lee, Sanghyun Byun, Mohanad Odema, Jung Guack, Jacob Song, Woo Seong Chung
Computation and Language
Hierarchical Alignment: Block-Level LoRA-DPO for Preference Tuning in Large Language Models
Yishen Chen, Qi Dong and Yukun Zhang
Preference tuning typically distributes adapter updates across every
Transformer layer. We study how the placement of a fixed LoRA budget affects Direct Preference Optimization (DPO). Hierarchical
Alignment partitions decoder depth into Local, Intermediate, and Global regions and restricts LoRA updates to a chosen contiguous block. Across Qwen and Llama models, three-seed sliding-window sweeps reveal broad low-loss basins around intermediate depth. Under exact trainableparameter matching, Middle achieves lower held-out DPO loss than an all-depth allocation on Qwen2.5-7B and Llama-3.1-8B. Generationlevel evidence is more variable. LLM judges and a blinded human study leave Selected versus All unresolved on Qwen; on Llama, two pairwise judges favor All while the human interval includes zero. Trained-adapter interventions show that learned depth components affect the optimization objective; removing the Llama Selected window also lowers generation quality. Across Qwen2.5 at 3B, 7B, and 14B, Middle versus All remains unresolved under Qwen3-Max; at 3B and 14B, both improve over Base. In our implementation, Middle also uses less peak
memory and takes shorter steps than a parameter-matched all-depth allocation. Together, the results support intermediate depth as a practical starting point for fixed-budget preference tuning, though the best window and its behavioral value still need per-setting validation.
Read the full abstract ▾
Computation and Language
POET: Preference Optimization for Enhanced Text-to-Image Generation
Ruibo Chen, Jiacheng Pan, Heng Huang et al. (+1 more)
Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified user
prompts due to a distributional gap with their descriptive training captions. This frequently leads to suboptimal image-text
alignment, aesthetics, and overall visual quality. To bridge this gap, we propose POET (Preference Optimization for Enhanced Text-to-Image generation), an automated
prompt rewriting framework that leverages large
language models (LLMs) to refine user inputs before feeding them into frozen T2I backbones. POET introduces a carefully designed composite reward system and an iterative Direct Preference Optimization (DPO) training pipeline, enabling the rewriter to learn model-preferred
prompt structures directly from
multimodal feedback without requiring costly high-quality supervised fine-tuning (SFT) data. Extensive evaluations across diverse T2I models and
benchmarks show that our
prompt rewriter consistently improves image-text
alignment, visual quality, and aesthetics, outperforming strong baselines. Furthermore, we demonstrate strong transferability by showing that a rewriter trained on one T2I backbone generalizes effectively to others without needing to be retrained. These findings highlight that POET is an effective, robust, and practical model-agnostic strategy for improving T2I systems.
Read the full abstract ▾
All authors Ruibo Chen, Jiacheng Pan, Heng Huang, Zhenheng Yang
Computation and Language
Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz et al. (+2 more)
The rapid advancement of large
language models (LLMs) has transformed the landscape of natural
language processing, enabling breakthroughs across a wide range of areas including question answering, machine translation, and text summarization. Yet, their deployment in real-world applications has raised concerns over reliability and trustworthiness, as LLMs remain prone to
hallucinations that produce plausible but factually incorrect outputs. Uncertainty quantification (UQ) has emerged as a central research direction to address this issue, offering principled measures for assessing the trustworthiness of model generations. We begin by introducing the foundations of UQ, from its formal definition to the traditional distinction between epistemic and aleatoric uncertainty, and then highlight how these concepts have been adapted to the context of LLMs. Building on this, we examine the role of UQ in
hallucination detection, where quantifying uncertainty provides a mechanism for identifying unreliable generations and improving reliability. We systematically categorize a wide spectrum of existing methods along multiple dimensions and present empirical results for several representative approaches. Finally, we discuss current limitations and outline promising future research directions, providing a clearer picture of the current landscape of LLM UQ for
hallucination detection.
Read the full abstract ▾
All authors Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Salman Avestimehr
Computation and Language
On the Interplay between Human Label Variation and Model Fairness
Kemal Kurniawan, Meladel Mistica, Timothy Baldwin et al. (+1 more)
The impact of human label variation (HLV) on model
fairness is an unexplored topic. This paper examines the interplay by comparing training on majority-vote labels with a range of HLV methods. Our experiments show that without explicit debiasing, HLV training methods have a positive impact on
fairness under certain configurations.
Read the full abstract ▾
All authors Kemal Kurniawan, Meladel Mistica, Timothy Baldwin, Jey Han Lau
Computation and Language
Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park et al. (+1 more)
Recent advancements in large
language models (LLMs) have shown strong performance in natural
language understanding and generation tasks. However, LLMs continue to encounter challenges with
hallucinations, where models generate plausible but incorrect information. While several factors contribute to
hallucinations, the impact of ill-formed
prompts,
prompts with ambiguous wording, incorrect grammar, or incomplete information, was relatively under explored. To address this, we introduce Multi-stage
Prompt Refinement (MPR), a framework designed to systematically improve these ill-formed
prompts across multiple stages. Each stage addresses specific errors such as punctuation, typographical mistakes, and misuse of key terms, using small
language models (SLMs) fine-tuned for these tasks. MPR iteratively enhances the clarity of
prompts with additional context and employs a self-reflection mechanism with ranking to prioritize the most relevant input. Experimental results on
hallucination benchmarks show that
prompts refined by MPR achieve over an 85~% win rate compared to their original forms, demonstrating its effectiveness in reducing
hallucinations and improving LLM output accuracy. Interestingly, we reveal that MPR can be combined with existing post-hoc
hallucination mitigation frameworks, further enhancing its versatility. MPR provides a lightweight and adaptable solution for enhancing LLM reliability across various domains.
Read the full abstract ▾
All authors Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee
Computation and Language
Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park et al. (+1 more)
Recent advancements in large
language models (LLMs) highlight their fluency in generating responses to diverse
prompts. However, these models sometimes generate plausible yet incorrect “hallucinated" facts, undermining trust. A frequent but often overlooked cause of such errors is the use of poorly structured or vague
prompts by users, leading LLMs to base responses on assumed rather than actual intentions. To mitigate
hallucinations induced by these ill-formed
prompts, we introduce Curative
Prompt Refinement (CPR), a plug-and-play framework for curative
prompt refinement that 1) cleans ill-formed
prompts, and 2) generates additional informative task descriptions to align the intention of the user and the
prompt using a fine-tuned small
language model. When applied to
language models, we discover that CPR significantly increases the quality of generation while also mitigating
hallucination. Empirical studies show that
prompts with CPR applied achieves over a 90% win rate over the original
prompts without any external knowledge.
Read the full abstract ▾
All authors Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee
Computation and Language
Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM
Alice Saebom Kwak, Maria Alexeeva, Gus Hahn-Powell et al. (+5 more)
The current trend in information extraction (IE) is to rely extensively on large
language models, effectively discarding decades of experience in building symbolic or statistical IE systems. This paper compares a neuro-symbolic (NS) and an LLM-based IE system in the agricultural domain, evaluating them on nine interviews across pork, dairy, and crop subdomains. The LLM-based system outperforms the NS one (F1 total: 69.4 vs. 52.7; core: 63.0 vs. 47.2), where total includes all extracted information and core focuses on essential details. However, each system has trade-offs: the NS approach offers faster runtime, greater control, and high accuracy in context-free tasks but lacks generalizability, struggles with contextual nuances, and requires significant resources to develop and maintain. The LLM-based system achieves higher performance, faster deployment, and easier maintenance but has slower runtime, limited control, model dependency and
hallucination risks. Our findings highlight the "hidden cost" of deploying NLP systems in real-world applications, emphasizing the need to balance performance, efficiency, and control.
Read the full abstract ▾
All authors Alice Saebom Kwak, Maria Alexeeva, Gus Hahn-Powell, Keith Alcock, Kevin McLaughlin, Doug McCorkle, Gabe McNunn, Mihai Surdeanu