English
Related papers

Related papers: When Contextual Inference Fails: Cancelability in …

200 papers

Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test…

Computation and Language · Computer Science 2019-04-15 Pierre Finnimore , Elisabeth Fritzsch , Daniel King , Alison Sneyd , Aneeq Ur Rehman , Fernando Alva-Manchego , Andreas Vlachos

Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization learn from direct rankings or numerical ratings of model outputs, these rankings are subjective, and a…

Computation and Language · Computer Science 2026-03-06 Nicholas Stranges , Yimin Yang

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM…

Machine Learning · Computer Science 2023-06-05 Eunji Kim , Dahuin Jung , Sangha Park , Siwon Kim , Sungroh Yoon

Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often…

Computation and Language · Computer Science 2025-08-08 Furui Cheng , Vilém Zouhar , Robin Shing Moon Chan , Daniel Fürst , Hendrik Strobelt , Mennatallah El-Assady

Concept-based explanations quantify how high-level concepts (e.g., gender or experience) influence model behavior, which is crucial for decision-makers in high-stakes domains. Recent work evaluates the faithfulness of such explanations by…

Computation and Language · Computer Science 2026-01-21 Gilat Toker , Nitay Calderon , Ohad Amosy , Roi Reichart

Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer, yet they often suffer reduced accuracy and concept leakage that undermines faithfulness. We…

Machine Learning · Computer Science 2026-02-17 Karim Galliamov , Syed M Ahsan Kazmi , Adil Khan , Adín Ramírez Rivera

Large Language Models (LLMs) are intended to reflect human linguistic competencies. But humans have access to a broad and embodied context, which is key in detecting and resolving linguistic ambiguities, even in isolated text spans. A…

Computation and Language · Computer Science 2025-10-22 Amber Shore , Russell Scheinberg , Ameeta Agrawal , So Young Lee

Although large language models (LLMs) have tremendous utility, trustworthiness is still a chief concern: models often generate incorrect information with high confidence. While contextual information can help guide generation, identifying…

Computation and Language · Computer Science 2025-10-07 Jiarui Liu , Jivitesh Jain , Mona Diab , Nishant Subramani

Idioms present a unique challenge for language models due to their non-compositional figurative interpretations, which often strongly diverge from the idiom's literal interpretation. In this paper, we employ causal tracing to systematically…

Computation and Language · Computer Science 2026-01-19 Soyoung Oh , Xinting Huang , Mathis Pink , Michael Hahn , Vera Demberg

Concept Bottleneck Models (CBMs) provide inherent interpretability by first mapping input samples to high-level semantic concepts, followed by a combination of these concepts for the final classification. However, the annotation of…

Machine Learning · Computer Science 2026-03-02 Yangyi Li , Mengdi Huai

Multi-turn instruction following capability constitutes a core competency of large language models (LLMs) in real-world applications. Existing evaluation benchmarks predominantly focus on fine-grained constraint satisfaction and…

Computation and Language · Computer Science 2025-06-02 Jinnan Li , Jinzhe Li , Yue Wang , Yi Chang , Yuan Wu

Constructing memory from users' long-term conversations overcomes LLMs' contextual limitations and enables personalized interactions. Recent studies focus on hierarchical memory to model users' multi-granular behavioral patterns via…

Multiagent Systems · Computer Science 2026-01-13 Wenyu Mao , Haosong Tan , Shuchang Liu , Haoyang Liu , Yifan Xu , Huaxiang Ji , Xiang Wang

Structured reasoning over natural language inputs remains a core challenge in artificial intelligence, as it requires bridging the gap between unstructured linguistic expressions and formal logical representations. In this paper, we propose…

Artificial Intelligence · Computer Science 2025-07-14 Keying Yang , Hao Wang , Kai Yang

Recent advancements in artificial intelligence have led to the creation of highly capable large language models (LLMs) that can perform tasks in a human-like manner. However, LLMs exhibit only infant-level cognitive abilities in certain…

Computation and Language · Computer Science 2024-09-25 Pengrui Han , Peiyang Song , Haofei Yu , Jiaxuan You

When engaging in collaborative tasks, humans efficiently exploit the semantic structure of a conversation to optimize verbal and nonverbal interactions. But in recent "language to code" or "language to action" models, this information is…

Computation and Language · Computer Science 2024-10-10 Akshay Chaturvedi , Kate Thompson , Nicholas Asher

Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or…

Computation and Language · Computer Science 2021-05-26 Theodore R. Sumers , Robert D. Hawkins , Mark K. Ho , Thomas L. Griffiths

We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user$\leftrightarrow$agent interaction. The interaction is a conversation between the user and…

Computation and Language · Computer Science 2024-10-14 David Castillo-Bolado , Joseph Davidson , Finlay Gray , Marek Rosa

Large Language Models (LLMs) have developed rapidly and are widely applied to both general-purpose and professional tasks to assist human users. However, they still struggle to comprehend and respond to the true user needs when intentions…

Computation and Language · Computer Science 2026-02-17 Minyuan Ruan , Ziyue Wang , Kaiming Liu , Yunghwei Lai , Peng Li , Yang Liu

Open-ended question answering (QA) evaluates a model's ability to perform contextualized reasoning beyond factual recall. This challenge is especially acute in practice-based domains, where knowledge is procedural and grounded in…

Computation and Language · Computer Science 2026-01-29 Si Chen , Le Huy Khiem , Annalisa Szymanski , Ronald Metoyer , Ting Hua , Nitesh V. Chawla

People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written…

Computation and Language · Computer Science 2026-03-13 Nadav Kunievsky , James A. Evans