United States

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy reduction, implicitly assuming that low uncertainty is desirable throughout reasoning. We show instead that reasoning efficiency is governed by the trajectory of uncertainty. CoTs with dominant downward entropy trends are substantially shorter. Motivated by this insight, we propose **E**ntropy **T**rend **R**eward (**ETR**), a trajectory-aware objective that encourages progressive uncertainty reduction while allowing limited local exploration. We integrate ETR into Group Relative Policy Optimization (GRPO) and evaluate it across multiple reasoning models and challenging benchmarks. ETR consistently achieves a superior accuracy–efficiency trade-off, improving DeepSeek-R1-Distill-7B by +9.9% accuracy while reducing CoT length by 67% across four benchmarks.

ACL 2026

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

## 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*

EMNLP 2025

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

technical paper

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamental pillar of this trustworthiness is calibration, which refers to an agent's ability to express confidence that reliably reflects its actual performance. While calibration is well-established for static models, its dynamics in tool-integrated agentic workflows remain under-explored. In this work, we systematically investigate verbalized calibration in tool-use agents, revealing a fundamental confidence dichotomy driven by tool type. Specifically, our pilot study identifies that evidence tools (e.g., web search) systematically induce severe overconfidence due to inherent noise in retrieved information, while verification tools (e.g., code interpreters) can ground reasoning through deterministic feedback and mitigate miscalibration. To robustly improve calibration across tool types, we propose a reinforcement learning (RL) fine-tuning framework that jointly optimizes task accuracy and calibration, supported by a holistic benchmark of reward designs. We demonstrate that our trained agents not only achieve superior calibration but also exhibit robust generalization from local training environments to noisy web settings and to distinct domains such as mathematical reasoning. Our results highlight the necessity of domain-specific calibration strategies for tool-use agents. More broadly, this work establishes a foundation for building self-aware agents that can reliably communicate uncertainty in high-stakes, real-world deployments.

The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents

Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity, undermining their utility in open-ended tasks like creative writing. Current methods lack explicit mechanisms for guiding diverse exploration and instead prioritize optimization efficiency and performance over diversity. This paper proposes an RL framework structured around a semi-structured long Chain-of-Thought (CoT), in which the generation process is decomposed into explicitly planned intermediate steps. We introduce a Diverse Planning Branching method that strategically introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. Experimental results on creative writing benchmarks demonstrate that our approach significantly improves output diversity without compromising generation quality, consistently outperforming existing baselines.

DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing

Retrieval-Augmented Generation (RAG) significantly enhances LLMs but faces high prefill latency during long-context processing. While KV cache reuse can mitigate this, current methods relying on shallow features or static heuristics often fail to identify critical tokens for recomputation, resulting in generation quality degradation.
We have an insight that KV deviations are more pronounced in deep layers.
However, directly extracting deep-layer features from the target model is computationally prohibitive. 
Crucially, we find that the deep-layer features of a lightweight speculative model exhibit strong consistency with the target model in the selection of critical tokens for recomputation.
In light of these insights, we propose SpecCache, which employs deep-layer hidden-state norms from a speculative model as a proxy to guide the critical token selection for target large model.
Experiments demonstrate that SpecCache outperforms state-of-the-art (SOTA) baselines. Compared to full KV recomputation, it reduces time-to-first-token (TTFT) by $2.17-3.95\times$ and increases inference throughput by $2.7-5.2\times$, with negligible degradation in generation quality relative to full recomputation.

SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these biases typically focus exclusively on response length, resulting in performance trade-offs. In this paper, we propose causally motivated intervention for mitigating multiple types of biases in RMs at inference time. Our method first identifies neurons whose activations are strongly correlated with predefined bias attributes, and applies neuron-level intervention that suppresses these signals. We evaluate our method on RM benchmarks and observe reductions in sensitivity to spurious features across diverse bias types, without inducing performance trade-offs. Moreover, when used for preference annotation, small RMs (2B and 7B) with our method, which edits less than 2\% of all the neurons in RMs, enable LLMs to improve alignment, achieving performance comparable to that of a state-of-the-art 70B RM on AlpacaEval and MT-Bench. Further analysis reveals that bias signals are primarily encoded by neurons in early layers, shedding light on the internal mechanisms of bias exploitation in RMs.

Debiasing Reward Models via Causally Motivated Inference-Time Intervention

A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. This tension is amplified by context-sensitive alignment: we observe that domain-specific contexts (e.g., chemistry) selectively relax defenses for domain-relevant harmful knowledge, while safety-research contexts (e.g., jailbreak studies) trigger broader relaxation spanning all harm categories. To systematically exploit this vulnerability, we propose Jargon, a framework combining safety-research contexts with multi-turn adversarial interactions that achieves attack success rates exceeding 93% across seven frontier models, including GPT-5.2, Claude-4.5, and Gemini-3, substantially outperforming existing methods. Activation space analysis reveals that Jargon queries occupy an intermediate region between benign and harmful inputs, a gray zone where refusal decisions become unreliable. To mitigate this vulnerability, we design a policy-guided safeguard that steers models toward helpful yet harmless responses, and internalize this capability through alignment fine-tuning, reducing attack success rates while preserving helpfulness.

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries

Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs.
A popular strategy is to assign a persona to the model to produce more varied, context-sensitive responses, similar to how responses vary across human individuals.
Against the expectation that persona prompting yields a wide range of opinions, our experiments show that LLMs keep consistent value orientations.
We observe a persistent inertia in their responses, where certain moral and value dimensions (especially harm avoidance and fairness) stay skewed in one direction across persona settings.
To study this, we use role-play at scale, which pairs randomized persona prompts with a macro-level analysis of model outputs.
Our results point to strong internal biases and value preferences in LLMs, which we call value orientation and inertia. These models warrant scrutiny and adjustment before use in applications where balanced outputs matter.

Inertia in Moral and Value Judgments of Large Language Models

The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting altruism. Traditional approaches must abstract away cognitive processes, leaving open how cognitive factors shape moral evolution. We introduce an LLM-based agent simulation framework that brings cognitive realism to this question: agents with varying moral dispositions perceive, remember, reason, and decide in a simulated prehistoric hunter-gatherer society. This enables us to manipulate factors that traditional models cannot represent---such as moral type observability and communication bandwidth---and to discover emergent cognitive mechanisms from agent interactions. Across 20 runs spanning four settings, we find that cooperation and mutual help are the central driver of evolutionary survival, with universal and reciprocal morality exhibiting the most stable outcomes across conditions while selfishness is strongly disfavoured. Beyond cooperation itself, we further identify cognition as a central mediator---most clearly through a cost of moral judgment that shifts the winning moral type across settings, with a self-purging effect among selfish agents as an additional cognitive pattern. We validate robustness across multiple LLM backbones, architecture ablations, and prompt sensitivity analyses. This work establishes LLM-based simulation as a powerful new paradigm to complement traditional research in evolutionary biology and anthropology, opening new avenues for investigating the complexities of moral and social evolution.

Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution

Story visualization requires generating a coherent sequence of images that collectively form a narrative, yet existing evaluation metrics and datasets often overlook visual continuity and narrative diversity. In this paper, we introduce the Visual Context-Aware Metric for Story Visualization, which uses large vision-language models to jointly assess caption fidelity and inter-image consistency, achieving Spearman’s correlation comparable to human agreement on two benchmarks. Also, to address the shortcomings of narrowly defined datasets with low diversity, we propose a diffusion-augmented evaluation pipeline that blends diverse and controlled narrative elements at adjustable ratios, producing challenging evaluation sets. By combining VCMS with this pipeline, we provide a scalable, human-aligned framework for evaluating story visualization models.

Evaluating Visual Narrative Coherence in Story Visualization via Diversified Storylines

End-to-end (E2E) spoken dialogue systems are replacing cascaded pipelines for voice-based human-AI interaction. Existing benchmarks primarily evaluate these systems on synthetic speech and single-turn tasks, leaving multi-turn conversational ability underexplored. We introduce Audio MultiChallenge an open-source benchmark to evaluate these systems under natural multi-turn interaction patterns. Building on the text-based MultiChallenge framework, which evaluates Inference Memory, Instruction Retention, and Self Coherence, we introduce a new axis Voice Editing that tests robustness to mid-utterance speech repairs and backtracking. We augment each axis to the audio modality, such as introducing Audio-Cue challenges for Inference Memory that require recalling ambient sounds and paralinguistic signals beyond semantic content. We curate 452 conversations from 47 speakers with 1,712 instance-specific rubrics through a hybrid pipeline that exposes model failures at scale while preserving natural disfluencies found in unscripted human speech. Our evaluation reveals that even frontier models struggle on our benchmark, with our highest-performing model achieving a 54.65% pass rate. Error analysis shows that models are not sufficiently robust to human speech when tracking instructions, edits, and audio cues, highlighting the need for improved audio-native multi-turn interaction capabilities.

Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction

We present a five-year case study of sentiment model selection for customer satisfaction (CSAT) prediction in B2B technical support. Our evaluation uses the complete population of CSAT-rated tickets from an enterprise software company: over 500 tickets comprising ${\sim}$2,500 customer comments from 100+ organizations over five years. We evaluate 17 approaches across 5 paradigms (lexicon, off-the-shelf transformers, NLI zero-shot, multi-task LLM agent, and 12 dedicated LLM agents from 6 vendor families), plus 11 fine-tuning experiments (all achieving MCC$\leq$0). Key findings: (1) a dedicated single-task LLM agent reduces neutral bias from 69% to 22%, improving MCC from $-$0.018 to 0.347 ($p$$<$0.001); (2) our results are consistent with the "Alignment Tax" (Lin et al., 2024; Wu et al., 2025) in sentiment classification: Claude Opus 4.6 exhibits 41% neutral predictions and lower recall than its budget model Haiku 4.5 ($p$=0.003); (3) ${\sim}$38% of dissatisfied customers are undetectable by all 12 LLMs due to administrative requests lacking emotional language; (4) Gemini 3 Flash achieves the best MCC (0.347) at $0.60/1K, over 100$\times$ cheaper than Claude Opus. We describe the three-phase production deployment and provide practitioner recommendations.

Downloads

Next from ACL 2026

The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents

Similar lecture

Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation