China

Large Language Models (LLMs) often exhibit hallucinations, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging step-by-step reasoning, but its impact on hallucination detection remains underexplored. To bridge this gap, we conduct a systematic empirical evaluation. We begin with a pilot experiment, revealing that CoT reasoning significantly affects the LLM&#39;s internal states and token probability distributions. Building on this, we evaluate the impact of various CoT prompting methods on mainstream hallucination detection methods across both instruction-tuned and reasoning-oriented LLMs. Specifically, we examine three key dimensions: changes in hallucination score distributions, variations in detection accuracy, and shifts in detection confidence. Our findings show that while CoT prompting helps reduce hallucination frequency, it also tends to obscure critical signals used for detection, impairing the effectiveness of various detection methods. Our study highlights an overlooked trade-off in the use of reasoning. Code is publicly available at: https://anonymous.4open.science/r/cot-hallu-detect .

EMNLP 2025

Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation

chain-of-thought

hallucination detection

large language models

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Large Language Models (LLMs) often exhibit hallucinations, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging step-by-step reasoning, but its impact on hallucination detection remains underexplored. To bridge this gap, we conduct a systematic empirical evaluation. We begin with a pilot experiment, revealing that CoT reasoning significantly affects the LLM's internal states and token probability distributions. Building on this, we evaluate the impact of various CoT prompting methods on mainstream hallucination detection methods across both instruction-tuned and reasoning-oriented LLMs. Specifically, we examine three key dimensions: changes in hallucination score distributions, variations in detection accuracy, and shifts in detection confidence. Our findings show that while CoT prompting helps reduce hallucination frequency, it also tends to obscure critical signals used for detection, impairing the effectiveness of various detection methods. Our study highlights an overlooked trade-off in the use of reasoning. Code is publicly available at: https://anonymous.4open.science/r/cot-hallu-detect .

poster

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Parameter-efficient fine-tuning (PEFT) is essential for adapting large language models (LLMs), with low rank adaptation (LoRA) being the most popular approach. However, LoRA suffers from slow convergence, and some recent LoRA variants, such as PiSSA, primarily rely on Singular Value Decomposition (SVD) for initialization, leading to expensive computation. To mitigate these problems, we resort to Nyström method, which follows a three-matrix manipulation. Therefore, we first introduce StructuredLoRA (SLoRA), investigating to introduce a small intermediate matrix between the low-rank matrices (A) and (B). Secondly, we propose NyströmLoRA (NLoRA), which leverages Nyström-based initialization for SLoRA to improve its effectiveness and efficiency. Finally, we propose IntermediateTune (IntTune) to explore fine-tuning exclusively the intermediate matrix of NLoRA to furthermore boost LLMs' efficiency. We evaluate our methods on 5 natural language generation (NLG) tasks and 8 natural language understanding (NLU) tasks. On GSM8K, SLoRA and NLoRA achieve accuracies of 56.48% and 57.70%, surpassing LoRA by 33.52% and 36.41% with only 3.67M additional trainable parameters. IntTune boosts average NLG performance over LoRA by 7.45% while using only 1.25% of its parameters. These results demonstrate the efficiency and effectiveness of our approach in enhancing model performance with minimal parameter overhead.

NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models

Critique ability, a meta-cognitive capability of humans, presents significant challenges for LLMs to improve. While utilizing human annotation can enhance critique ability effectively, most recent works primarily rely on supervised fine-tuning (SFT) using critiques generated by a single LLM like GPT-4, which is more scalable and cost-effective. However, such model-generated critiques often suffer from inherent flaws due to the complexity of critique. Consequently, fine-tuning LLMs on these flawed critiques not only limits performance but also propagates errors into the learned model. To address this issue, we propose \textbf{MultiCritique}, a unified framework that leverages multi-agent feedback to improve critique ability in both the supervised fine-tuning (SFT) and reinforcement learning (RL) stages. In the SFT stage, MultiCritique aggregates high-quality multi-agent critiques through a fine-grained meta-critique mechanism. In the RL stage, preference critiques are constructed and refined by validating their contributions to revisions, thereby enhancing robustness of RL in improving critique ability. Based on MultiCritique, we construct SFT and RL datasets. Extensive experimental results on two benchmarks highlight the key benefits of our dataset, including superior quality, enhanced data efficiency, strong generalization on unseen tasks, and improvements in the general capability of LLMs. Notably, our fine-tuned 7B model significantly surpasses advanced 7B-13B models, approaching advanced 70B LLMs and GPT-4. Codes and datasets will be publicly available.

Training Language Models to Critique With Multi-agent Feedback

Existing key–value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns and task performance, which can lead to degraded generalization. In this paper, we propose EvolKV, an adaptive framework for layer-wise, task-driven KV cache compression that jointly optimizes the memory efficiency and task performance. By reformulating cache allocation as a multi-objective optimization problem, EvolKV leverages evolutionary search to dynamically configure layer budgets while directly maximizing downstream performance. Extensive experiments across eight tasks demonstrate that our method outperforms all baseline methods across a wide range of KV cache sizes on long-context tasks and surpasses heuristic baselines by up to 7 percentage points on GSM8K. Notably, EvolKV achieves comparable or superior performance to full KV cache methods on code completion while utilizing only 1.5% of the original budget, suggesting the untapped potential in learned compression strategies for KV cache budget allocation.

EvolKV: Evolutionary KV Cache Compression for LLM Inference

Lossless compression techniques are crucial in an era of rapidly growing data. Traditional universal compressors like gzip offer low computational overhead, high speed, and broad applicability across data distributions. However, they often lead to worse compression rates than modern neural compressors, which leverage large-scale training data to model data distributions more effectively. Despite their advantages, neural compressors struggle to generalize to unseen data. To address this limitation, we propose a novel framework that performs Test-Time Steering via a Weighted Product of Experts (wPoE). At inference, our method adaptively combines a universal compression model with a pretrained neural language model, ensuring the compression rate is at least as good as the best individual model. Extensive experiments demonstrate that our approach improves the performance of text compression without requiring fine-tuning. Furthermore, it seamlessly integrates with any autoregressive language model, providing a practical solution for enhancing text compression across diverse data distributions.

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts

The evaluation of cross-lingual semantic search capabilities of models is often limited to existing datasets from tasks such as information retrieval and semantic textual similarity. To allow for domain-specific evaluation, we introduce Cross Lingual Semantic Discrimination (CLSD), a novel cross-lingual semantic search task that does not require a large evaluation corpus, only parallel sentences of the language pair of interest within the target domain. This task focuses on the ability of a model to cross-lingually rank the true parallel sentence higher than challenging distractors generated by a large language model. We create a case study of our introduced CLSD task for the language pair German-French in the news domain. Within this case study, we find that models that are also fine-tuned for retrieval tasks benefit from pivoting through English, while bitext mining models perform best directly cross-lingually. A fine-grained similarity analysis enabled by our distractor generation strategy indicate that different embedding models are sensitive to different types of perturbations.

Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examples

The auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. While recent research has explored various speculative decoding techniques for multi-token generation, these methods introduce high memory costs from the additional weights and KV cache of separate draft models, limiting efficiency in edge and long-context scenarios. To overcome these limitations in edge-scale LLMs, we propose a novel parallel prompt decoding that requires only runtime memory overhead by employing a unified single model for both speculation and verification. Inspired by the human natural language generation process, PPD approximates outputs generated at future timesteps in parallel by using multiple prompt tokens. Furthermore, we present a hardware-aware two-stage tree pruning algorithm that adaptively optimizes this decoding scheme to fully leverage the computational capacities on different GPUs. Through extensive experiments across LLMs ranging from MobileLlama to Vicuna-13B on a wide range of benchmarks, our approach demonstrates up to 2.49 times speedup. Moreover, our parallel prompt decoding can serve as an orthogonal optimization for synergistic integration with existing speculative decoding, showing up to 1.22 times further speed improvement. To support future development, we have included our code implementation with this submission.

Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference

Self-correction has demonstrated potential in code generation by allowing language models to revise and improve their outputs through successive refinement. Recent studies have explored prompting-based strategies that incorporate verification or feedback loops using proprietary models, as well as training-based methods that leverage their strong reasoning capabilities. However, whether smaller models possess the capacity to effectively guide their outputs through self-reflection remains unexplored. Our findings reveal that smaller models struggle to exhibit reflective revision behavior across both self-correction paradigms. In response, we introduce CoCoS, an approach designed to enhance the ability of small language models for multi-turn code correction. Specifically, we propose an online reinforcement learning objective that trains the model to confidently maintain correct outputs while progressively correcting incorrect outputs as turns proceed. Our approach features an accumulated reward function that aggregates rewards across the entire trajectory and a fine-grained reward better suited to multi-turn correction scenarios. This facilitates the model in enhancing initial response quality while achieving substantial improvements through self-correction. With 1B-scale models, CoCoS achieves improvements of 35.8% on the MBPP and 27.7% on HumanEval compared to the baselines.

Self-Correcting Code Generation Using Small Language Models

Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label alone is insufficient: it reveals little about the model’s reasoning and offers limited interpretability. To address this, we reframe table–text alignment as an explanation task, requiring models to identify the table cells essential for claim verification. We build a new dataset by extending the SciTab benchmark with human-annotated cell-level rationales. Annotators verify the claim label and highlight the minimal set of cells needed to support their decision. After the annotation process, we utilize the collected information and propose a taxonomy for handling ambiguous cases. Our experiments show that (i) incorporating table alignment information improves claim verification performance, and (ii) most LLMs, while often predicting correct labels, fail to recover human-aligned rationales, suggesting that their predictions do not stem from faithful reasoning.

Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers

Knowledge Base Question Answering (KBQA) is a fundamental task that enables natural language interaction with structured knowledge bases (KBs).Given a natural language question, KBQA aims to retrieve the answers from the KB. However, existing approaches, including retrieval-based, semantic parsing-based methods and large-language model-based methods often suffer from generating non-executable queries and inefficiencies in query execution. To address these challenges, we propose GRV-KBQA, a three-stage framework that decouples logical structure generation from semantic grounding and incorporates structure-aware validation to enhance accuracy. Unlike previous methods, GRV-KBQA explicitly enforces KB constraints to improve alignment between generated logical forms and KB structures. Experimental results on WebQSP and CWQ show that GRV-KBQA significantly improves performance over existing approaches. The ablation study conducted confirms the effectiveness of the decoupled logical form generation and validation mechanism of our framework.

GRV-KBQA: A Three-Stage Framework for Knowledge Base Question Answering with Decoupled Logical Structure, Semantic Grounding and Structure-Aware Validation

For individuals who have experienced traumatic events such as strokes, speech may no longer be a viable means of communication. While text-to-speech (TTS) can be used as a communication aid since it generates synthetic speech, it fails to preserve the user’s own voice. As such, face-to-voice (FTV) synthesis, which derives corresponding voices from facial images, provides a promising alternative. However, existing methods rely on pre-trained visual encoders, and finetune them to align with speech embeddings, which strips fine-grained information from facial inputs such as gender or ethnicity, despite their known correlation with vocal traits. Moreover, these pipelines are multi-stage, which requires separate training of multiple components, thus leading to training inefficiency. To address these limitations, we utilize fine-grained facial attribute modeling by decomposing facial images into non-overlapping segments and progressively integrating them into a multi-granular representation. This representation is further refined through multi-task learning of speaker attributes such as gender and ethnicity at both the visual and acoustic domains. Moreover, to improve alignment robustness, we adopt a multi-view training strategy by pairing various visual perspectives of a speaker in terms of different angles and lighting conditions, with identical speech recordings. Extensive subjective and objective evaluations confirm that our approach substantially enhances face-voice congruence and synthesis stability.

Downloads

Next from EMNLP 2025

NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models

Similar lecture

Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters