Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized approach to LLM alignment is its lack of scalability, as it involves repeatedly acquiring preference data and training new reward models and LLMs for each individual's preferences. To address these challenges, we propose a new paradigm where users specify what they value most within the system message, steering the LLM's generation behavior to better align with the user's intentions. However, a naive application of such an approach is non-trivial since LLMs are typically trained on a uniform system message (e.g., "You are a helpful assistant"), which limitstheir ability to generalize to diverse, unseen system messages. To improve this generalization, we create Multifaceted Collection, augmenting 66k user instructions into 197k system messages through hierarchical user value combinations. Using this dataset, we train a 7B LLM called Janus and test it on 921 prompts from 5 benchmarks (AlpacaEval 2.0, FLASK, Koala, MT-Bench, and Self-Instruct)by adding system messages that reflect unseen user values. JANUS achieves tie+win rate of 75.2%, 72.4%, and 66.4% against Mistral 7B Instruct v0.2, GPT-3.5 Turbo, and GPT-4, respectively. Unexpectedly, on three benchmarks focused on response helpfulness (AlpacaEval 2.0, MT-Bench, Arena Hard Auto v0.1), JANUS also outperforms LLaMA 3 8B Instruct by a +4.0%p, +0.1%p, +3.0%p margin, underscoring that training with a vast array of system messages could also enhance alignment to the general public's preference as well. Our code, dataset, benchmark, and models are available at https://lklab.kaist.ac.kr/Janus/.

While AI-generated text (AIGT) detectors achieve over 90\% accuracy on direct LLM outputs, they fail catastrophically against iteratively-paraphrased content. We investigate why iteratively-paraphrased text -- itself AI-generated -- evades detection systems designed for AIGT identification. Through intrinsic mechanism analysis, we reveal that iterative paraphrasing creates an intermediate laundering region characterized by semantic displacement with preserved generation patterns, which brings up two attack categories: paraphrasing human-authored text (authorship obfuscation) and paraphrasing LLM-generated text (plagiarism evasion). To address these vulnerabilities, we introduce PADBen, the first benchmark systematically evaluating detector robustness against both paraphrase attack scenarios. PADBen comprises a five-type text taxonomy capturing the full trajectory from original content to deeply laundered text, and five progressive detection tasks across sentence-pair and single-sentence challenges. We evaluate 11 state-of-the-art detectors, revealing critical asymmetry: detectors successfully identify the plagiarism evasion problem but fail for the case of authorship obfuscation. Our findings demonstrate that current detection approaches cannot effectively handle the intermediate laundering region, necessitating fundamental advances in detection architectures beyond existing semantic and stylistic discrimination methods. For detailed code implementation, please see https://github.com/JonathanZha47/PadBen-Paraphrase-Attack-Benchmark.

Test-time scaling improves large language models (LLMs) on long-horizon reasoning tasks by allocating more compute at inference. LLM Inference via Tree Search (LITS) methods achieve strong performance but are highly inefficient, often running an order of magnitude slower than iterative approaches. We propose Chain-in-Tree (CiT), a plug-in framework that decides when to branch during search rather than expanding at every step. CiT introduces lightweight Branching Necessity (BN) evaluations: BN-DP (Direct Prompting), where an auxiliary LLM judges branching needs, and BN-SC (Self-Consistency), which clusters candidate actions to assess agreement. Integrated into Tree of Thoughts, ReST-MCTS, and RAP, BN-DP achieves 75-85% reductions in token generation, model calls, and runtime on GSM8K and Math500, with often negligible or no accuracy loss. BN-SC typically yields substantial savings (up to 80%) generally but shows instability in 1-4 out of 14 settings, caused by a small subset of examples that produce extremely long reasoning steps. We theoretically prove that BN-DP never increases policy invocations and release both modular LITS implementations and a lightweight CiT function applicable across all LITS variants. The full codebase is publicly available at https://github.com/xinzhel/chain_in_tree.

First submitted: 30 Oct 2023. The final version will be available open access via the journal. Abstract This study explores the use of generative AI for automating the classification of tutors' Dialogue Acts (DAs), aiming to reduce the time and effort required by traditional manual coding. This case study uses the open - source CIMA corpus, in which tutors' re sponses are pre - annotated into four DA categories. Both GPT - 3.5 - turbo and GPT - 4 models were tested using tailored prompts. Results show that GPT - 4 achieved 80% accuracy, a weighted F1 - score of 0.81, and a Cohen's Kappa of 0.74, surpassing baseline performa nce and indicating substantial agreement with human annotations. These findings suggest that generative AI has strong potential to provide an efficient and accessible approach to DA classification, with meaningful implications for educational dialogue analysis. The study also highlights the importance of task - specific label definitions and contextual information in enhanc ing the quality of automated annotation. Finally, it underscores the ethical considerations associated with the use of generative AI and the need for responsible and transparent research practices.

As large language models (LLMs) increasingly interact with each other, most notably in multi-agent setups, we may expect (and hope) that `trust' relationships develop between them, mirroring trust relationships between human colleagues, friends, or partners. Yet, though prior work has shown LLMs to be capable of identifying emotional connections and recognizing reciprocity in trust games, little remains known about (i) how different strategies to build trust compare, (ii) how such trust can be measured implicitly, and (iii) how this relates to explicit measures of trust. We study these questions by relating implicit measures of trust, i.e. susceptibility to persuasion and propensity to collaborate financially, with explicit measures of trust, i.e. a dyadic trust questionnaire well-established in psychology. We build trust in three ways: by building rapport dynamically, by starting from a prewritten script that evidences trust, and by adapting the LLMs' system prompt. Surprisingly, we find that the measures of explicit trust are either little or highly negatively correlated with implicit trust measures. These findings suggest that measuring trust between LLMs by asking their opinion may be deceiving. Instead, context-specific and implicit measures may be more informative in understanding how LLMs trust each other.

This paper details the CardiffNLP team's contribution to the CLEARS shared task on Spanish text adaptation, hosted by IberLEF 2025. The shared task contained two subtasks and the team submitted to both. Our team took an LLM-prompting approach with different prompt variations. While we initially experimented with LLaMA-3.2, we adopted Gemma-3 for our final submission, and landed third place in Subtask 1 and second place in Subtask 2. We detail our numerous prompt variations, examples, and experimental results.

The rise of Large Reasoning Models (LRMs) promises a significant leap forward in language model capabilities, aiming to tackle increasingly sophisticated tasks with unprecedented efficiency and accuracy. However, despite their impressive performance, recent studies have highlighted how current reasoning models frequently fail to generalize to novel, unseen problems, often resorting to memorized solutions rather than genuine inferential reasoning. Such behavior underscores a critical limitation in modern LRMs, i.e., their tendency toward overfitting, which in turn results in poor generalization in problem-solving capabilities. In this paper, we introduce Nexus Architect, an enhanced iteration of our multi-agent system framework, Nexus, equipped with a novel automated workflow synthesis mechanism. Given a user's prompt and a small set of representative examples, the Architect autonomously generates a tailored reasoning workflow by selecting suitable strategies, tool integrations, and adversarial techniques for a specific problem class. Furthermore, the Architect includes an iterative prompt refinement mechanism that fine-tunes agents' system prompts to maximize performance and improve the generalization capabilities of the system. We empirically evaluate Nexus Architect by employing an off-the-shelf, non-reasoning model on a custom dataset of challenging logical questions and compare its performance against state-of-the-art LRMs. Results show that Nexus Architect consistently outperforms existing solutions, achieving up to a 66% increase in pass rate over Gemini 2.5 Flash Preview, nearly 2.5$\times$ against Claude Sonnet 4 and DeepSeek-R1, and over 3$\times$ w.r.t. Llama 4 Scout.

Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized approach to LLM alignment is its lack of scalability, as it involves repeatedly acquiring preference data and training new reward models and LLMs for each individual's preferences. To address these challenges, we propose a new paradigm where users specify what they value most within the system message, steering the LLM's generation behavior to better align with the user's intentions. However, a naive application of such an approach is non-trivial since LLMs are typically trained on a uniform system message (e.g., "You are a helpful assistant"), which limitstheir ability to generalize to diverse, unseen system messages. To improve this generalization, we create Multifaceted Collection, augmenting 66k user instructions into 197k system messages through hierarchical user value combinations.