English
Related papers

Related papers: Why do you think that? Exploring Faithful Sentence…

200 papers

Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions.…

Computation and Language · Computer Science 2026-05-26 Yoav Gur-Arieh , Ana Marasović , Mor Geva

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales…

Computation and Language · Computer Science 2024-05-01 Yunlong Feng , Yang Xu , Libo Qin , Yasheng Wang , Wanxiang Che

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We…

Computation and Language · Computer Science 2023-09-22 Qing Lyu , Shreya Havaldar , Adam Stein , Li Zhang , Delip Rao , Eric Wong , Marianna Apidianaki , Chris Callison-Burch

Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a…

Computation and Language · Computer Science 2022-05-19 Liyan Tang , Dhruv Rajan , Suyash Mohan , Abhijeet Pradhan , R. Nick Bryan , Greg Durrett

Large language models (LLMs) increasingly produce natural language explanations, yet these explanations often lack faithfulness, and they do not reliably reflect the evidence the model uses to decide. We introduce FaithLM, a model-agnostic…

Computation and Language · Computer Science 2025-10-28 Yu-Neng Chuang , Guanchu Wang , Chia-Yuan Chang , Ruixiang Tang , Shaochen Zhong , Fan Yang , Mengnan Du , Xuanting Cai , Vladimir Braverman , Xia Hu

Natural language explanations in recommender systems are often framed as a review generation task, leveraging user reviews as ground-truth supervision. While convenient, this approach conflates a user's opinion with the system's reasoning,…

Information Retrieval · Computer Science 2025-08-08 S. M. F. Sani , Asal Meskin , Mohammad Amanlou , Hamid R. Rabiee

When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved this choice depends on how well-known the fact is. We ask: does the model's chain-of-thought…

Computation and Language · Computer Science 2026-05-28 Pruthvinath Jeripity Venkata

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Computation and Language · Computer Science 2025-03-18 Alihan Hüyük , Xinnuo Xu , Jacqueline Maasch , Aditya V. Nori , Javier González

Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are…

Computation and Language · Computer Science 2023-07-03 Pepa Atanasova , Oana-Maria Camburu , Christina Lioma , Thomas Lukasiewicz , Jakob Grue Simonsen , Isabelle Augenstein

Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability. However, despite their plausibility, they may not reflect the model's true reasoning faithfully.…

Computation and Language · Computer Science 2025-12-29 Kerem Zaman , Shashank Srivastava

Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such…

Machine Learning · Computer Science 2021-09-09 Pepa Atanasova , Jakob Grue Simonsen , Christina Lioma , Isabelle Augenstein

Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…

Human-Computer Interaction · Computer Science 2026-03-10 Xin Sun , Shu Wei , Jos A Bosch , Isao Echizen , Saku Sugawara , Abdallah El Ali

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…

Computation and Language · Computer Science 2021-12-07 George Chrysostomou , Nikolaos Aletras

Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches require ground-truth labels to seed or filter these traces -…

We study the source of uncertainty in DeepSeek R1-32B by analyzing its self-reported verbal confidence on question answering (QA) tasks. In the default answer-then-confidence setting, the model is regularly over-confident, whereas semantic…

Computation and Language · Computer Science 2025-11-06 Jakub Podolak , Rajeev Verma

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly improved the performance of Large Language Models (LLMs) on tasks requiring multi-step reasoning. However, most RLVR pipelines rely on sparse outcome-based rewards,…

Computation and Language · Computer Science 2026-02-13 Runquan Gui , Yafu Li , Xiaoye Qu , Ziyan Liu , Yeqiu Cheng , Yu Cheng

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Computation and Language · Computer Science 2025-12-09 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters. To make this reasoning process more explicit, recent works…

Computation and Language · Computer Science 2023-04-10 Peifeng Wang , Aaron Chan , Filip Ilievski , Muhao Chen , Xiang Ren

The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to…

Machine Learning · Computer Science 2026-01-29 Tianyi Alex Qiu , Micah Carroll , Cameron Allen

Free-text rationales justify model decisions in natural language and thus become likable and accessible among approaches to explanation across many tasks. However, their effectiveness can be hindered by misinterpretation and hallucination.…

Computation and Language · Computer Science 2025-06-04 Yi-Sheng Hsu , Nils Feldhus , Sherzod Hakimov