Austria

Large language models (LLMs) often suffer from hallucinations, posing significant challenges for real-world applications. Confidence calibration, as an effective indicator of hallucination, is thus essential to enhance the trustworthiness of LLMs. Prior work mainly focuses on short-form tasks using a single response-level score (macro calibration), which is insufficient for long-form outputs that may contain both accurate and inaccurate claims. In this work, we systematically study atomic calibration, which evaluates factuality calibration at a fine-grained level by decomposing long responses into atomic claims. We further categorize existing confidence elicitation methods into discriminative and generative types, and propose two new confidence fusion strategies to improve calibration. Our experiments demonstrate that LLMs exhibit poorer calibration at the atomic level during long-form generation. More importantly, atomic calibration uncovers insightful patterns regarding the alignment of confidence methods and the changes of confidence throughout generation. This sheds light on future research directions for confidence estimation in long-form generation.

ACL 2025

Atomic Calibration of LLMs in Long-Form Generations

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

workshop paper

### 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.

Please log in

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) have achieved great success, but their occasional content fabrication, or hallucination, limits their practical application. Hallucination arises because LLMs struggle to admit ignorance due to inadequate training on knowledge boundaries. We call it a limitation of LLMs that they can not accurately express their knowledge boundary, answering questions they know while admitting ignorance to questions they do not know. In this paper, we aim to teach LLMs to recognize and express their knowledge boundary, so they can reduce hallucinations caused by fabricating when they do not know. We propose CoKE, which first probes LLMs' knowledge boundary via internal confidence given a set of questions, and then leverages the probing results to elicit the expression of the knowledge boundary. Extensive experiments show CoKE helps LLMs express knowledge boundaries, answering known questions while declining unknown ones, significantly improving in-domain and out-of-domain performance.

Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals

Despite Large Language Models' advances, document-grounded generation still suffers from factual errors. Current evaluations oversimplify error analysis by applying binary judgements, while costly human-annotated datasets contain under-representative error distributions. To address these challenges, we propose a novel framework named SIS-Fact (Systematic, Interpretable and Scalable Factuality Evaluation), which integrates systematic error typologies, synthetic data generation pipelines, and high-quality interpretable annotations for comprehensive factuality evaluation. Specifically, we first develop ten diverse methods to synthesize six error types in grounded generation, including both intrinsic and extrinsic errors. In this way, we develop SIS-Fact Dataset, a high-quality document-grounded factuality evaluation dataset characterized by challenging errors and interpretable error analysis. Based on SIS-Fact Dataset, we introduce SIS-Fact Evaluator, an advanced factuality evaluation model capable of fine-grained analysis and correction. Our extensive experiments show that SIS-Fact Evaluator achieves SOTA performance in SIS-Fact Dataset while maintaining strong generalization across existing multiple factuality benchmarks.

SIS-Fact: Towards Systematic, Interpretable and Scalable Factuality Evaluation for LLM

Large language models (LLMs) encode vast amounts of knowledge during pre-training (parametric knowledge, or PK) and can further be enhanced by incorporating contextual knowledge (CK). Can LLMs effectively integrate their internal PK with external CK to solve complex problems? In this paper, we investigate the dynamic interaction between PK and CK, categorizing their relationships into four types: Supportive, Complementary, Conflicting, and Irrelevant. To support this investigation, we introduce ECHOQA, a benchmark spanning scientific, factual, and commonsense knowledge. Our results show that LLMs tend to suppress their PK when contextual information is available, even when it is complementary or irrelevant. While tailored instructions can encourage LLMs to rely more on their PK, they still struggle to fully leverage it. These findings reveal a key vulnerability in LLMs, raising concerns about their reliability in knowledge-intensive tasks. We will release our code and dataset to facilitate future research.

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models

Evaluating foundation models for crystallographic reasoning requires benchmarks that isolate generalization behavior while enforcing physical constraints. This work introduces, xCrysAlloys, a multiscale multicrystal dataset with two physically grounded evaluation protocols to stress-test multimodal generative models. The Spatial-Exclusion benchmark withholds all supercells of a given radius from a diverse dataset, enabling controlled assessments of spatial interpolation and extrapolation. The Compositional-Exclusion benchmark omits all samples of a specific chemical composition, probing generalization across stoichiometries. Nine vision--language foundation models are prompted with crystallographic images and textual context to generate structural annotations. Responses are evaluated via (i) relative errors in lattice parameters and density, (ii) a physics-consistency index penalizing volumetric violations, and (iii) a hallucination score capturing geometric outliers and invalid space-group predictions. These benchmarks establish a reproducible, physically informed framework for assessing generalization, consistency, and reliability in large-scale multimodal models. Dataset and implementation are available at https://github.com/KurbanIntelligenceLab/StressTestingMMFMinCR.

Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning

We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the importance of each modality in the instruction tuning stage, often using a majority of vision-language data while keeping text-only data limited and fixing mixtures of modalities. By incorporating diverse text-only data in the visual instruction tuning stage, we vary vision-language data in various controlled experiments to investigate the importance of modality in visual instruction tuning. Our comprehensive evaluation shows that the text-heavy instruction tuning approach is able to perform on par with traditional vision-heavy mixtures on both modalities across 12 general datasets while using as low as half the total training tokens. We find that simply increasing sufficiently diverse text-only data enables transfer of instruction following ability and domain knowledge across modalities while being more efficient than the vision-language approach.

MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models

Artificial intelligence agents when deployed to solve complex problems, need to first decompose the task into smaller manageable sub-tasks, and further associate tools if one is required to solve the sub-task. If the size of the set of tools to chose from is large, a retrieval system is usually employed to narrow down the tool choices before the LLM can proceed with associating tools to the sub-tasks. This paper focuses on the retrieval problem to identify the set of relevant tools to solve a complex task given a large pool of tools to chose from using retrieval augmented generation (RAG) and we refer to it as ToolReAGT. The proposed approach employs ReAct prompting to perform the retrieval in an iterative fashion to first identify if a tool is required and then associate one or more tools for each sub-task. This deviates from conventional RAG where an n-best list of tools are identified given the complex task directly. Experiments are presented on the UltraTool benchmark corpus with 1000 complex tasks and over 2000 tools to select from. A conventional RAG-system is established as baseline and compared to the ToolReAGt approach, resulting in an 8.9% improved retrieval accuracy score recall@5.

ToolReAGt: Tool Retrieval for LLM-based Complex Task Solution via Retrieval Augmented Generation

Large language models (LLMs) often demonstrate strong performance by leveraging implicit knowledge acquired during pretraining. Analogical reasoning, which solves new problems by referencing similar known examples, offers a structured way to utilize this knowledge, but can also lead to subtle factual errors and hallucinations. In this work, we investigate whether LLMs can recognize the reliability of their own analogical outputs using black-box uncertainty estimation (UE). We evaluate six UE metrics across two reasoning-intensive tasks: mathematical problem solving (GSM8K) and code generation (Codeforces). Our results show that Kernel Language Entropy (KLE) and Lexical Similarity (LexSim) are the most robust indicators of correctness. Moreover, while analogical prompting increases model confidence over direct prompting, most uncertainty arises during the analogy transfer step. These findings highlight the limitations of analogical knowledge transfer in LLMs and demonstrate the potential of UE methods for detecting hallucinated reasoning in black-box settings.

Can LLMs Recognize Their Own Analogical Hallucinations? Evaluating Uncertainty Estimation for Analogical Reasoning

We present Meetalk, a retrieval-augmented and knowledge-adaptive system for generating personalized meeting minutes. Although large language models (LLMs) excel at summarizing, their output often lacks faithfulness and does not reflect user-specific structure and style. Meetalk addresses these issues by integrating ASR-based transcription with LLM generation guided by user-derived knowledge. Specifically, Meetalk maintains and updates three structured databases, Table of Contents, Chapter Allocation, and Writing Style, based on user-uploaded samples and editing feedback. These serve as a dynamic memory that is retrieved during generation to ground the model’s outputs. To further enhance reliability, Meetalk introduces hallucination-aware uncertainty markers that highlight low-confidence segments for user review. In a user study in five real-world meeting scenarios, Meetalk significantly outperforms a strong baseline (iFLYTEK ASR + ChatGPT-4o) in completeness, contextual relevance, and user trust. Our findings underscore the importance of knowledge foundation and feedback-driven adaptation in building trustworthy, personalized LLM systems for high-stakes summarization tasks.

Meetalk: Retrieval-Augmented and Adaptively Personalized Meeting Summarization with Knowledge Learning from User Corrections

Large language models (LLMs) have shown strong performance across natural language reasoning tasks, yet their reasoning processes remain brittle and difficult to interpret. Prompting techniques like Chain-of-Thought (CoT) enhance reliability by eliciting intermediate reasoning steps or aggregating multiple outputs. However, they lack mechanisms for enforcing logical structure and assessing internal coherence. We introduce Theorem-of-Thought (ToTh), a novel framework that models reasoning as collaboration among three parallel agents, each simulating a distinct mode of inference: abductive, deductive, and inductive. Each agent produces a reasoning trace, which is structured into a formal reasoning graph. To evaluate consistency, we apply Bayesian belief propagation guided by natural language inference (NLI), assigning confidence scores to each step. The most coherent graph is selected to derive the final answer. Experiments on symbolic (WebOfLies) and numerical (MultiArith) reasoning benchmarks show that ToTh consistently outperforms CoT, Self-Consistency, and CoT-Decoding across multiple LLMs, while producing interpretable and logically grounded reasoning chains. Our findings suggest a promising direction for building more robust and cognitively inspired LLM reasoning. The implementation is available at https://github.com/KurbanIntelligenceLab/theorem-of-thought.

Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models

Chinese homophones, prevalent in Internet culture, bring rich linguistic twists that are challenging for language models. While native speakers disambiguate them through phonological reasoning and contextual understanding, it remains untested how well LLMs perform on this task and whether LLMs also achieve this via similar reasoning processes or merely through memorization of homophone-original word pairs during training.

In this paper, we present HomoP-CN, the first Chinese Internet homophones dataset with systematic perturbations for evaluating LLMs' homophone restoration capabilities. Using this benchmark, we investigated the influence of semantic, phonological, and graphemic features on LLMs' restoration accuracy, measured the reliance levels of each model on memorization during restoration through consistency ratios under controlled perturbations, and assessed the effectiveness of various prompting strategies, including contextual cues, pinyin augmentation, few-shot learning, and thought-chain approaches.

Downloads

Next from ACL 2025

Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals

Similar lecture

Calibrating Long-form Generations From Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2025

Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals

Similar lecture

Calibrating Long-form Generations From Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads