Austria

When using agent-task datasets to enhance agent capabilities for Large Language Models (LLMs), current methodologies often treat all tokens within a sample equally. However, we argue that tokens serving different roles—specifically, reasoning tokens versus boilerplate tokens (e.g., those governing output format)—differ significantly in importance and learning complexity, necessitating their disentanglement and distinct treatment. To address this, we propose a novel Shuffle-Aware Discriminator (SHAD) for adaptive token discrimination. SHAD classifies tokens by exploiting predictability differences observed after shuffling input-output combinations across samples: boilerplate tokens, due to their repetitive nature among samples, maintain predictability, whereas reasoning tokens do not. Using SHAD, we propose the Reasoning-highlighted Fine-Tuning (RFT) method, which adaptively emphasizes reasoning tokens during fine-tuning, yielding notable performance gains over common Supervised Fine-Tuning (SFT).

ACL 2025

Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning

tool use

agent

large language models

reasoning

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

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 AAAI 2026". 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 are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

AAAI 2026

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

poster

### 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.

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

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

Large Language Models (LLMs) often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. Maintaining a balance between domain-specific enhancements and general model utility is a key challenge. This paper proposes a novel approach named APT (Weakness Case Acquisition and Iterative Preference Training) to enhance domain-specific performance with self-generated dis-preferred weakness data (bad cases and similar cases). APT uniquely focuses on training the model using only those samples where errors occur, alongside a small, similar set of samples retrieved for this purpose. This targeted training minimizes interference with the model’s existing knowledge base, effectively retaining generic capabilities. Experimental results on the LLama-2 and Mistral-V0.3 models across various benchmarks demonstrate that APT ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to various existing methods. This validates our method as an effective strategy for enhancing domain-specific capabilities without sacrificing the model's broader applicability.

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training

Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role's pre-defined ability limits. Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-playing in instruction-following scenarios. We introduce a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, including: (1) Multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages; (2) Role-playing machine reading comprehension, involving response, refusal, and attempts according to passage answerability and role ability; (3) More complex scenarios with nested, multi-turn and prioritized instructions. The final RoleMRC features a 10.2k role profile meta-pool, 37.9k well-synthesized role-playing instructions, and 1.4k testing samples. We develop a pipeline to quantitatively evaluate the fine-grained role-playing and instruction-following capabilities of several mainstream LLMs, as well as models that are fine-tuned on our data. Moreover, cross-evaluation on external role-playing datasets confirms that models fine-tuned on RoleMRC enhances instruction-following without compromising general role-playing and reasoning capabilities. We also probe the neural-level activation maps of different capabilities over post-tuned LLMs. Access to our RoleMRC, RoleMRC-mix and Codes: https://github.com/LuJunru/RoleMRC.

RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following

Large Language Models (LLMs) are increasingly deployed as autonomous agents for simulation and decision-making, necessitating a deeper understanding of their decision-making behaviour under risk. We investigate the relationship between LLMs' personality traits and risk-propensity, applying Cumulative Prospect Theory (CPT) and the Big Five personality framework. We compare the behaviour of several LLMs to human baselines. Our findings show that the majority of the models investigated are risk-neutral rational agents, whilst displaying higher Conscientiousness and Agreeableness traits, coupled with lower Neuroticism. Interventions on Big Five traits, particularly Openness, influence the risk-propensity of several LLMs. Advanced models mirror human personality-risk patterns, suggesting that cognitive biases can be surfaced by optimal prompting. However, their distilled variants show no cognitive bias, suggesting limitations to knowledge transfer processes. Notably, Openness emerges as the most influential factor to risk-propensity, aligning with human baselines. In contrast, less advanced models demonstrate inconsistent generalization of the personality-risk relationship. This research advances our understanding of LLM behaviour under risk and highlights the potential and limitations of personality-based interventions in shaping LLM decision-making.

How Personality Traits Shape LLM Risk-Taking Behaviour

Attributing answers to source documents is an approach used to enhance the verifiability of a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on improving and evaluating the attribution quality of large language models (LLMs) in RAG, but this may come at the expense of inducing biases in the attribution of answers. We define and examine two aspects in the evaluation of LLMs in RAG pipelines, namely attribution sensitivity and bias with respect to authorship information. We explicitly inform an LLM about the authors of source documents, instruct it to attribute its answers, and analyze (i) how sensitive the LLM's output is to the author of source documents, and (ii) whether the LLM exhibits a bias towards human-written or AI-generated source documents. We design an experimental setup in which we use counterfactual evaluation to study three LLMs in terms of their attribution sensitivity and bias in RAG pipelines. Our results show that adding authorship information to source documents can significantly change the attribution quality of LLMs by 3 to 18%. We show that LLMs can have an attribution bias towards explicit human authorship, which can serve as a competing hypothesis for findings of prior work that shows that LLM-generated content may be preferred over human-written contents. Our findings indicate that metadata of source documents can influence LLMs' trust, and how they attribute their answers. Furthermore, our research highlights attribution bias and sensitivity as a novel aspect of the vulnerability of LLMs.

Evaluation of Attribution Bias in Generator-Informed Retrieval-Augmented Large Language Models

Grammatical Error Correction (GEC) involves detecting and correcting the wrong usage of grammar. While large language models (LLMs) with in-context learning (ICL) capabilities have shown significant progress on various natural language processing (NLP) tasks, their few-shot performance on GEC remains suboptimal. This is mainly due to the challenge of retrieving suitable in-context demonstrations that capture error patterns instead of semantic similarity. In this paper, we demonstrate that LLMs can inherently capture information related to grammatical errors through their internal states. From these states, we extract the Grammatical Error Representation (GER), an informative and semantically neutral encoding of grammatical errors. Our novel GER-based retrieval method significantly boosts performance in ICL settings on multilingual GEC datasets, improving the precision of correction. For high-resource languages, our results on 8B-sized open-source models match those of closed-source models such as Deepseek2.5 and GPT-4o-mini. For low-resource languages, our F0.5 scores surpass the baseline by up to a factor of 1.2. This method provides a more precise and resource-efficient solution for multilingual GEC, offering a promising direction for interpretable GEC research.

Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction

Interpreting the internal process of neural models has long been a challenge. This challenge remains relevant in the era of large language models (LLMs) and in-context learning (ICL); for example, ICL poses a new issue of interpreting which example in the few-shot examples contributed to identifying/solving the task. To this end, in this paper, we design synthetic diagnostic tasks of inductive reasoning, inspired by the generalization tests in linguistics; here, most in-context examples are ambiguous w.r.t. their underlying rule, and one critical example disambiguates the task demonstrated. The question is whether conventional input attribution (IA) methods can track such a reasoning process, i.e., identify the influential example, in ICL. Our experiments provide several practical findings; for example, a certain simple IA method works the best, and the larger the model, the generally harder it is to interpret the ICL with gradient-based IA methods.

Can Input Attributions Interpret the Inductive Reasoning Process in In-Context Learning?

Personalizing Large Language Models (LLMs) has become a critical step in facilitating their widespread application to enhance individual life experiences. In pursuit of personalization, distilling key preference information from an individual's historical data as instructional preference context to customize LLM generation has emerged as a promising direction. However, these methods face a fundamental limitation by overlooking the inter-user comparative analysis, which is essential for identifying the inter-user differences that truly shape preferences. To address this limitation, we propose Difference-aware Personalization Learning (DPL), a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. DPL strategically selects representative users for comparison and establishes a structured standard to extract meaningful, task-relevant differences for customizing LLM generation. Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. We release our code on Anonymous GitHub https://anonymous.4open.science/r/DPL-2111.

Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization

The current project is inscribed within the field of stemmatology or the study and/or reconstruction of textual transmission based on the relationship between the available witnesses of given texts. In particular, the variants (differences) at the word-level in manuscripts written in Biblical Hebrew are considered. A strong classifier (F1 value of 0.80) is trained to predict the category of difference between word pairs ('plus/minus', 'inversion', 'morphological', 'lexical' or 'unclassifiable') as present in collated (aligned) pairs of witnesses. The classifier is non-neural and makes use of the two words themselves as well as part-of-speech (POS) tags, hand-crafted rules per category and synthetically derived data. Other models experimented with include neural ones based on the state-of-the-art model for Modern Hebrew, DictaBERT. Other features whose relevance is tested are different types of morphological information pertaining to the word pairs and the Levenshtein distance between words. A selection of the strongest classifiers as well as the used synthetic data and the steps taken at its derivation are made available. Coincidentally, the corelation between two sets of morphological labels is investigated: professionally established as per the Qumran-Digital online library and automatically derived with the sub-model DictaBERT-morph.

A Classifier of Word-Level Variants in Witnesses of Biblical Hebrew Manuscripts

Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions due to their limited ability in acquiring external knowledge for innovation. To address this problem, we introduce an enhanced planning and search methodology designed to boost the creative potential of LLM-based systems. Our approach involves an iterative process to purposely plan the retrieval of external knowledge, progressively enriching the idea generation with broader and deeper insights. Validation through automated and human assessments demonstrates that our framework substantially elevates the quality of generated ideas, particularly in novelty and diversity. The number of unique novel ideas produced by our framework is 3.4 times higher than without it. Moreover, our method outperforms the current state-of-the-art, generating at least 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation. Our code is available in [Anonymous Github Repository](https://anonymous.4open.science/r/Nova-4CA8/README.md) Repository.
A demo of our work can be found at [Nova](https://www.nova.vin/).

NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Models

In real-world applications, large language models (LLMs) often need to handle diverse and complex instructions. Specifically, when instructions are subject to multiple constraints, some of which are somewhat ambiguous, LLMs often fail to produce answers that satisfy all constraints, limiting their effectiveness in various tasks. To address this challenge, we examine the different constraints in the instructions and discover that the difficulty of determining whether an answer meets a constraint varies widely, from extremely straightforward to exceptionally perplexing. Correspondingly, we propose to assign constraints to different constraint levels. Furthermore, inspired by chain-of-thought (CoT) and self-taught reasoner (STaR), we propose a two-stage method named CARE-STaR (Constraint-AwaRE STaR). Our method distinguishes constraints within instructions by generating different CoTs and guides LLMs to autonomously learn optimal answers by setting the positive rewards to the CoTs that are beneficial to generating accurate answers and iteratively optimizing these answers. We have conducted extensive experiments on three instruction-following benchmarks, taking three existing LLMs as base LLMs, respectively. Experimental results indicate that our method substantially enhances the capability of these LLMs to handle complex instructions, outperforming supervised fine-tuning (SFT). Our code is available at https://github.com/lzl0124/carestar.

Downloads

Next from ACL 2025

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training

Similar lecture

Identifying and Analyzing Performance-Critical Tokens in Large Language Models