Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignment strategy that prioritizes high-impact tokens within preference pairs, leveraging token-level log-probability differences between the current policy and a reference model. By focusing on these informative tokens, our approach reduces computational overhead and enhances alignment fidelity. We further explore the role of reference model quality, demonstrating that stronger reference models significantly improve token selection accuracy and overall optimization effectiveness. Comprehensive experiments on benchmarks such as Arena-Hard and MT-Bench validate the superiority of our Selective-DPO method over standard DPO and distillation-based baselines. Our findings highlight the importance of token-level optimization and reference model selection in advancing preference alignment for LLMs. The code is available at https://github.com/Dongzhijin/SDPO.

Text embeddings are fundamental to many natural language processing (NLP) tasks, extensively applied in domains such as recommendation systems and information retrieval (IR). Traditionally, transmitting embeddings instead of raw text has been seen as privacy-preserving. However, recent methods such as Vec2Text challenge this assumption by demonstrating that controlled decoding can successfully reconstruct original texts from black-box embeddings. The unexpectedly strong results reported by Vec2Text motivated us to conduct further verification, particularly considering the typically non-intuitive and opaque structure of high-dimensional embedding spaces. In this work, we reproduce the Vec2Text framework and evaluate it from two perspectives: (1) validating the original claims, and (2) extending the study through targeted experiments. First, we successfully replicate the original key results in both in-domain and out-of-domain settings, with only minor discrepancies arising due to missing artifacts, such as model checkpoints and dataset splits. Furthermore, we extend the study by conducting a parameter sensitivity analysis, evaluating the feasibility of reconstructing sensitive inputs (e.g., passwords), and exploring embedding quantization as a lightweight privacy defense. Our results show that Vec2Text is effective under ideal conditions, capable of reconstructing even password-like sequences that lack clear semantics. However, we identify key limitations, including its sensitivity to input sequence length. We also find that Gaussian noise and quantization techniques can mitigate the privacy risks posed by Vec2Text, with quantization offering a simpler and more widely applicable solution. Our findings emphasize the need for caution in using text embeddings and highlight the importance of further research into robust defense mechanisms for NLP systems.

Large vision-language models (LVLMs) have demonstrated remarkable capabilities by integrating pre-trained vision encoders with large language models (LLMs). Similar to single-modal LLMs, chain-of-thought (CoT) prompting has been adapted for LVLMs to enhance multi-modal reasoning by generating intermediate rationales based on visual and textual inputs. While CoT is assumed to improve grounding and accuracy in LVLMs, our experiments reveal a key challenge: existing LVLMs often ignore the contents of generated rationales in CoT reasoning. To address this, we re-formulate multi-modal CoT reasoning as a KL-constrained reward maximization focused on rationale-conditional log-likelihood. As the optimal solution, we propose rationale-enhanced decoding (RED), a novel plug-and-play inference-time decoding strategy. RED harmonizes visual and rationale information by multiplying distinct image-conditional and rationale-conditional next token distributions. Extensive experiments show that RED consistently and significantly improves reasoning over standard CoT and other decoding methods across multiple benchmarks and LVLMs. Our work offers a practical and effective approach to improve both the faithfulness and accuracy of CoT reasoning in LVLMs, paving the way for more reliable rationale-grounded multi-modal systems.

Large Language Models (LLMs) have demonstrated outstanding performance across a range of NLP tasks, however, their computational demands hinder their deployment in real-world, resource-constrained environments. This work investigates the extent to which LLMs can be compressed using Knowledge Distillation (KD) while maintaining strong performance on Question Answering (QA) tasks. We evaluate student models distilled from the Pythia and Qwen2.5 families on two QA benchmarks, SQuAD and MLQA, under zero-shot and one-shot prompting conditions. Results show that student models retain over 90% of their teacher models' performance while reducing parameter counts by up to 57.1%. Furthermore, one-shot prompting yields additional performance gains over zero-shot setups for both model families. These findings underscore the trade-off between model efficiency and task performance, demonstrating that KD, combined with minimal prompting, can yield compact yet capable QA systems suitable for resource-constrained applications.

Document Image Machine Translation (DIMT) aims to translate text within document images, facing generalization challenges due to limited training data and the complex interplay between visual and textual information. To address these challenges, we introduce M4Doc, a novel single-to-mix modality alignment framework leveraging Multimodal Large Language Models (MLLMs). M4Doc aligns an image-only encoder with the multimodal representations of an MLLM, pre-trained on large-scale document image datasets. This alignment enables a lightweight DIMT model to learn crucial visual-textual correlations during training. During inference, M4Doc bypasses the MLLM, maintaining computational efficiency while benefiting from its multimodal knowledge. Comprehensive experiments demonstrate substantial improvements in translation quality, especially in cross-domain generalization and challenging document image scenarios.

Large vision-language models (VLMs) increasingly adopt post-training techniques such as long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL) to elicit sophisticated reasoning. While these methods exhibit synergy in language-only models, their joint effectiveness in VLMs remains uncertain. We present a systematic investigation into the distinct roles and interplay of long-CoT SFT and RL across multiple multimodal reasoning benchmarks. We find that SFT improves performance on difficult questions by in-depth, structured reasoning, but introduces verbosity and degrades performance on simpler ones. In contrast, RL promotes generalization and brevity, yielding consistent improvements across all difficulty levels, though the improvements on the hardest questions are less prominent compared to SFT. Surprisingly, combining them through two-staged, interleaved, or progressive training strategies, as well as data mixing and model merging, all fails to produce additive benefits, instead leading to trade-offs in accuracy, reasoning style, and response length. This "synergy dilemma" highlights the need for more seamless and adaptive approaches to unlock the full potential of combined post-training techniques for reasoning VLMs.Figure 1: Accuracy gains from various post-training techniques across five difficulty levels (L1, easy to L5, hard) on five multimodal reasoning benchmarks. Long-CoT SFT boosts Qwen2.5-VL-7B on harder questions but hurts easier ones, while RL yields steady gains across the board. Hybrid strategies consistently trade off strengths rather than achieving true synergy. Large language models (LLMs) like OpenAI's o1/o3 (Jaech et al., 2024) and DeepSeek-R1 (Guo et al., 2025) have demonstrated remarkable reasoning abilities by thinking before answering .

This position paper explores pluri-perspectivism as a core element of human creative experience and its relevance to human-robot co-creativity. We propose a layered, five-dimensional model to guide the design of co-creative behaviors and the analysis of interaction dynamics. This model is based on literature and results from an interview study we conducted with 10 visual artists and 8 arts educators, examining how pluri-perspectivism supports creative practice. The findings of this study provide insight how robots could enhance human creativity through adaptive, context-sensitive behavior, demonstrating the potential of pluri-perspectivism. This paper outlines future directions for integrating pluri-perspectivism with vision-language models (VLMs), to support context sensitivity in co-creative robots.

What algorithms do LLMs actually learn and use to solve problems? Studies addressing this question are sparse, as research priorities are focused on improving performance through scale, leaving a theoretical and empirical gap in understanding emergent algorithms. This position paper proposes AlgEval: a framework for systematic research into the algorithms that LLMs learn and use. AlgEval aims to uncover algorithmic primitives, reflected in latent representations, attention, and inference-time compute, and their algorithmic composition to solve task-specific problems. We highlight potential methodological paths and a case study toward this goal, focusing on emergent search algorithms. Our case study illustrates both the formation of top-down hypotheses about candidate algorithms, and bottom-up tests of these hypotheses via circuit-level analysis of attention patterns and hidden states. The rigorous, systematic evaluation of how LLMs actually solve tasks provides an alternative to resource-intensive scaling, reorienting the field toward a principled understanding of underlying computations. Such algorithmic explanations offer a pathway to human-understandable interpretability, enabling comprehension of the model's internal reasoning performance measures. This can in turn lead to more sample-efficient methods for training and improving performance, as well as novel architectures for end-to-end and multi-agent systems.

This paper presents a competitive approach to multilingual subjectivity detection using large language models (LLMs) with few-shot prompting. We participated in Task 1: Subjectivity of the CheckThat! 2025 evaluation campaign. We show that LLMs, when paired with carefully designed prompts, can match or outperform fine-tuned smaller language models (SLMs), particularly in noisy or low-quality data settings. Despite experimenting with advanced prompt engineering techniques, such as debating LLMs and various example selection strategies, we found limited benefit beyond well-crafted standard few-shot prompts. Our system achieved top rankings across multiple languages in the CheckThat! 2025 subjectivity detection task, including first place in Arabic and Polish, and top-four finishes in Italian, English, German, and multilingual tracks. Notably, our method proved especially robust on the Arabic dataset, likely due to its resilience to annotation inconsistencies. These findings highlight the effectiveness and adaptability of LLM-based few-shot learning for multilingual sentiment tasks, offering a strong alternative to traditional fine-tuning, particularly when labeled data is scarce or inconsistent.

The oxygen reduction reaction (ORR) catalyst plays a critical role in enhancing fuel cell efficiency, making it a key focus in material science research. However, extracting structured information about ORR catalysts from vast scientific literature remains a significant challenge due to the complexity and diversity of textual data. In this study, we propose a named entity recognition (NER) and relation extraction (RE) approach using DyGIE++ with multiple pre-trained BERT variants, including MatSciBERT and PubMedBERT, to extract ORR catalyst-related information from the scientific literature, which is compiled into a fuel cell corpus for materials informatics (FC-CoMIcs). A comprehensive dataset was constructed manually by identifying 12 critical entities and two relationship types between pairs of the entities. Our methodology involves data annotation, integration, and fine-tuning of transformer-based models to enhance information extraction accuracy. We assess the impact of different BERT variants on extraction performance and investigate the effects of annotation consistency. Experimental evaluations demonstrate that the fine-tuned PubMedBERT model achieves the highest NER F1-score of 82.19% and the MatSciBERT model attains the best RE F1-score of 66.10%. Furthermore, the comparison with human annotators highlights the reliability of fine-tuned models for ORR catalyst extraction, demonstrating their potential for scalable and automated literature analysis. The results indicate that domain-specific BERT models outperform general scientific models like BlueBERT for ORR catalyst extraction.