English
Related papers

Related papers: Truth as a Trajectory: What Internal Representatio…

200 papers

Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of complex reasoning tasks. Additionally, theoretical proofs…

Computation and Language · Computer Science 2023-11-21 Zhuosheng Zhang , Yao Yao , Aston Zhang , Xiangru Tang , Xinbei Ma , Zhiwei He , Yiming Wang , Mark Gerstein , Rui Wang , Gongshen Liu , Hai Zhao

Large Language Models (LLMs) often display overconfidence, presenting information with unwarranted certainty in high-stakes contexts. We investigate the internal basis of this behavior via mechanistic interpretability. Using open-sourced…

Machine Learning · Computer Science 2025-09-03 Hikaru Tsujimura , Arush Tagade

Large reasoning models (LRMs) have significantly advanced performance on complex tasks, yet their tendency to overthink introduces inefficiencies. This study investigates the internal mechanisms of reinforcement learning (RL)-trained LRMs…

Artificial Intelligence · Computer Science 2025-05-22 Rongzhi Zhu , Yi Liu , Zequn Sun , Yiwei Wang , Wei Hu

The emergence of large language models (LLMs) such as ChatGPT and Claude presents new challenges for philosophy of language, particularly regarding the nature of linguistic meaning and representation. While LLMs have traditionally been…

Computation and Language · Computer Science 2025-06-27 Yuzuki Arai , Sho Tsugawa

In autoregressive large language models (LLMs), temporal straightening offers an account of how the next-token prediction objective shapes representations. Models learn to progressively straighten the representational trajectory of input…

Artificial Intelligence · Computer Science 2026-04-28 Jack King , Evelina Fedorenko , Eghbal A. Hosseini

We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs. Although several approaches based on entropy or…

Computation and Language · Computer Science 2024-02-29 Fan Yin , Jayanth Srinivasa , Kai-Wei Chang

Human logic has gradually shifted from intuition-driven inference to rigorous formal systems. Motivated by recent advances in large language models (LLMs), we explore whether LLMs exhibit a similar evolution in the underlying logical…

Artificial Intelligence · Computer Science 2026-01-27 Zhengqing Zang , Yuqi Ding , Yanmei Gu , Changkai Song , Zhengkai Yang , Guoping Du , Junbo Zhao , Haobo Wang

We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models. Differently from previously existing tools that focus on isolated parts of the…

Computation and Language · Computer Science 2024-04-11 Igor Tufanov , Karen Hambardzumyan , Javier Ferrando , Elena Voita

Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM's…

Computation and Language · Computer Science 2024-06-06 Shaolei Zhang , Tian Yu , Yang Feng

Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from…

Robotics · Computer Science 2024-09-25 Mike Zhang , Kaixian Qu , Vaishakh Patil , Cesar Cadena , Marco Hutter

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while…

Computation and Language · Computer Science 2024-10-08 Taiming Lu , Muhan Gao , Kuai Yu , Adam Byerly , Daniel Khashabi

Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals…

Computation and Language · Computer Science 2026-04-16 Wen Luo , Guangyue Peng , Wei Li , Shaohang Wei , Feifan Song , Liang Wang , Nan Yang , Xingxing Zhang , Jing Jin , Furu Wei , Houfeng Wang

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

Computation and Language · Computer Science 2025-05-27 Zhihong Pan , Kai Zhang , Yuze Zhao , Yupeng Han

A central question in multilingual language modeling is whether large language models (LLMs) develop a universal concept representation, disentangled from specific languages. In this paper, we address this question by analyzing latent…

Computation and Language · Computer Science 2025-06-26 Clément Dumas , Chris Wendler , Veniamin Veselovsky , Giovanni Monea , Robert West

We introduce TASER (Translation Assessment via Systematic Evaluation and Reasoning), a metric that uses Large Reasoning Models (LRMs) for automated translation quality assessment. TASER harnesses the explicit reasoning capabilities of LRMs…

Computation and Language · Computer Science 2025-10-02 Monishwaran Maheswaran , Marco Carini , Christian Federmann , Tony Diaz

In this work, we address question answering (QA) over a hybrid of tabular and textual data that are very common content on the Web (e.g. SEC filings), where discrete reasoning capabilities are often required. Recently, large language models…

Computation and Language · Computer Science 2024-10-01 Fengbin Zhu , Ziyang Liu , Fuli Feng , Chao Wang , Moxin Li , Tat-Seng Chua

Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can…

Machine Learning · Computer Science 2026-04-24 Haoqiang Kang , Yizhe Zhang , Nikki Lijing Kuang , Nicklas Majamaki , Navdeep Jaitly , Yi-An Ma , Lianhui Qin

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Computation and Language · Computer Science 2025-09-29 Zheng Wei Lim , Alham Fikri Aji , Trevor Cohn

While large language models (LLMs) have demonstrated remarkable abilities across various fields, hallucination remains a significant challenge. Recent studies have explored hallucinations through the lens of internal representations,…

Computation and Language · Computer Science 2024-12-30 Junteng Liu , Shiqi Chen , Yu Cheng , Junxian He

As large language models (LLMs) move from static reasoning tasks toward dynamic environments, their success depends on the ability to navigate and respond to an environment that changes as they interact at inference time. An underexplored…

Computation and Language · Computer Science 2026-02-19 Annie Wong , Aske Plaat , Thomas Bäck , Niki van Stein , Anna V. Kononova