How Do LLMs Change Predictions Under Negation?

Jongwook Yoon; Jongwon Lim; Sungjib Lim; Woojin Cho; Yohan Jo

cs.CLOct 7, 2026

How Do LLMs Change Predictions Under Negation?

Authors: Jongwook Yoon, Jongwon Lim, Sungjib Lim, Woojin Cho, Yohan Jo

Organizations: Graduate School of Data Science, Seoul National University · Department of Computer Science and Engineering, Seoul National University

Abstract

Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source and closed-source LLMs on our negation benchmark and find that, in 37-71% of cases, they repeat the same answer under negation (e.g., "Madrid" for "What is not the capital of Spain?"). To understand and address this brittleness, we mechanistically examine how models operate under negation. Our main finding is that specialized attention heads and MLP neurons jointly implement negation by (1) suppressing retrieval of the original answer (e.g., "Madrid") while (2) promoting a favored candidate within the answer category (e.g., "Paris"). This contrasts with accounts of human negation processing, in which information about the original answer helps to determine what should be excluded. Furthermore, we find that this difference from human processing is a key source of negation failures: the model's mechanism relies on suppressing the original answer rather than using it to determine what to exclude, so the model can repeat the original answer when suppression is too weak or when a bias toward particular answers prevents it from selecting an alternative. To address this weakness in the model's negation mechanism, we propose a training objective that requires larger shifts in answer preference for more confident original predictions, and show that it reduces negation failures with less degradation of general capabilities than standard fine-tuning baselines. Together, our results demonstrate how mechanistic analysis can reveal why a linguistic capability fails and guide training that targets the underlying limitation.

Figures & tables

Figure 1: Overview of LLMs’ negation mechanism. Left: The negation signal triggers three downstream changes: (A) suppressing the original answer, (B) promoting answer category information, and (C) promoting a category-specific alternative. Right: These changes preserve the answer category subspace while shifting preference to an alternative answer (“Paris”).

	Factual Association		Logical Reasoning		Visual Question Answering		Average
	PopQA	RippleEdits	PhantomWiki	SynthWorlds	GQA	PTR	Negated
Model	Ans. change / Cat. pres.	Ans. change / Cat. pres.	Ans. change / Cat. pres.	Ans. change / Cat. pres.	Ans. change / Cat. pres.	Ans. change / Cat. pres.	Ans. change / Cat. pres.	Original acc.
Open-source models
Gemma 3-4B-IT	40.8 / 98.5	14.1 / 95.7	66.4 / 90.8	35.0 / 90.3	46.3 / 93.0	31.8 / 97.3	39.1 / 94.3	32.6
Gemma 3-12B-IT	58.1 / 99.7	31.1 / 95.9	50.4 / 96.2	42.3 / 95.2	58.3 / 94.9	44.4 / 99.1	47.4 / 96.8	41.9
Gemma 3-27B-IT	68.2 / 99.9	44.8 / 98.8	70.1 / 99.6	42.9 / 95.4	77.5 / 94.1	72.5 / 98.9	62.6 / 97.8	44.8

Table 1: Answer change and category preservation rates on the test split of our benchmark (%). Averages are computed over six benchmarks for multimodal models and four for text-only models.

Figure 2: Left: Answer change rates decrease with confidence in the original answer (mean token log-probability; results averaged across six open-source models). Right: Answer change rates are also lower when the original answer is the model’s most common response under negation.

Figure 3: Removing the negation direction in Gemma 3-12B-IT. (a) Layerwise effects of steering with the negation signal (

\beta=1

), overlaid with negation-delta similarity. (b) Causal effects of steering with the negation signal at (L24). (c) Cosine similarity between attention and MLP output changes induced by natural negation and by steering (

\beta=3

). Effects are averaged over six benchmarks. Shading indicates 95% bootstrap intervals.

Figure 4: Components involved in forming alternatives in Gemma 3-12B-IT. (a) Cumulative head and neuron scores. (b) Effects of restoring their non-negated values, averaged across six benchmarks; dots show matched random controls. (c) Unfiltered logit lens top/bottom five for an illustrative example.

Figure 5: Negation largely preserves the shared answer category structure (a–b), while redirecting candidate-space representations toward a specific direction (c–d). Arrows show independently computed activations without centering or normalization.

	In-domain (ID)				Out-of-domain (OOD)				General Capability
Method	Answer change	Category preservation	Answer diversity	Original accuracy	Answer change	Category preservation	Answer diversity	Original accuracy	Avg.
Base	58.14	99.71	90.90	21.90	46.93	96.64	80.05	37.15	78.04
ALiT (ours)	96.55	99.86	86.54	22.10	84.96	97.63	76.26	37.40	77.68
Unlikelihood	99.95 ( $+3.40$ )	53.97 ( $-45.89$ )	75.21 ( $-11.33$ )	21.16 ( $-0.94$ )	89.41 ( $+4.45$ )	57.68 ( $-39.95$ )	84.46 ( $+8.20$ )	37.40 ( $0.00$ )	77.95 ( $+0.27$ )
SFT	96.84 ( $+0.29$ )	100.00 ( $+0.14$ )	8.03 ( $-78.51$ )	21.64 ( $-0.46$ )	86.52 ( $+1.56$ )	99.06 ( $+1.43$ )	39.11 ( $-37.15$ )	36.64 ( $-0.76$ )	76.98 ( $-0.70$ )
DPO	100.00 ( $+3.45$ )	42.76 ( $-57.10$ )	73.61 ( $-12.93$ )	21.97 ( $-0.13$ )	99.23 ( $+14.27$ )	52.63 ( $-45.00$ )	83.71 ( $+7.45$ )	37.16 ( $-0.24$ )	77.36 ( $-0.32$ )

Table 2: Training results for Gemma 3-12B-IT (%). ID denotes PopQA, and OOD denotes five other benchmarks.

Appendix figures & tables28 assets

Supplementary material from the paper’s appendix.

Appendix

Form	Prompt
PopQA Original answer: New Delhi
Original	What is the capital of India?
not	What is not the capital of India?
n’t	What isn’t the capital of India?
never	What is never the capital of India?
by no means	What is by no means the capital of India?

Appendix

Table 3: Examples of all four negation forms from each source benchmark, drawn from the training split. Bold text marks the negation expression. Original answers are source references, not targets for the negated prompts. Underlines indicate completion slots for display. Supporting documents are omitted; the corresponding GQA and PTR images appear in Figure 6 .

Panel of Figure 6 — Figure 6: Images accompanying the visual examples in Table 3 . The same image is used for the original prompt and all four negated variants.

Validation Criterion	PASS	FAIL	FAIL Rate (%)
Grammaticality	125,527	1,229	0.97
Unambiguity	120,329	6,427	5.07
Negation Scope Fidelity	105,330	21,426	16.90
Overall	105,048	21,708	17.13

Appendix

Table 4: Benchmark validation results for the negation benchmark dataset. Overall rejection indicates that a record was rejected if it failed at least one validation criterion.

Benchmark	Original	PASS	PASS Rate (%)
PopQA	45,476	37,426	82.30
RippleEdits	18,488	14,150	76.54
PhantomWiki	6,660	5,668	85.11
SynthWorlds	1,120	840	75.00
GQA	21,112	15,912	75.37
PTR	33,900	31,052	91.60

Appendix

Table 5: Benchmark validation results by source benchmark. Original denotes the number of examples in the original benchmark, while PASS denotes the number of examples that passed our filtering process. We also report the corresponding pass rate.

Validation Criterion	Unanimous PASS	Unanimous FAIL	Unanimous Agreement (%)
Grammaticality	237 (98.75%)	2 (0.83%)	99.58%
Unambiguity	237 (98.75%)	0 (0.00%)	98.75%
Negation Scope Fidelity	174 (72.50%)	11 (4.58%)	77.08%
Overall	648 (90.00%)	13 (1.81%)	91.81%

Appendix

Table 6: Human–human agreement for benchmark validation by validation criterion. Percentages are calculated over all criterion-level decisions within each validation criterion.

Validation Criterion	Agreed PASS	Agreed FAIL	Human–LLM Agreement (%)
Grammaticality	230 (95.83%)	2 (0.83%)	96.67%
Unambiguity	217 (90.42%)	0 (0.00%)	90.42%
Negation Scope Fidelity	185 (77.08%)	18 (7.50%)	84.58%
Overall	632 (87.78%)	20 (2.78%)	90.56%

Appendix

Table 7: Human–LLM agreement for benchmark validation by validation criterion. Agreed PASS and Agreed FAIL indicate decisions for which the human majority label and the LLM label were identical. Percentages are calculated over all decisions within each criterion.

Evaluation Criterion	Unanimous PASS	Unanimous FAIL	Unanimous Agreement (%)
Original Answer Correctness	91 (37.92%)	135 (56.25%)	94.17%
Repetition Under Negation	95 (39.58%)	132 (55.00%)	94.58%
Negated Answer Category Validity	179 (74.58%)	23 (9.58%)	84.17%
Overall	365 (50.69%)	290 (40.28%)	90.97%

Appendix

Table 8: Human–human agreement for negation evaluation by evaluation criterion. Percentages are calculated over all criterion-level decisions within each evaluation criterion.

Evaluation Criterion	Agreed PASS	Agreed FAIL	Human–LLM Agreement (%)
Original Answer Correctness	96 (40.00%)	137 (57.08%)	97.08%
Repetition Under Negation	62 (60.78%)	38 (37.25%)	98.04%
Negated Answer Category Validity	33 (84.62%)	0 (0.00%)	84.62%
Overall	191 (50.13%)	175 (45.93%)	96.06%

Appendix

Table 9: Human–LLM agreement for negation evaluation by evaluation criterion. Agreed PASS and Agreed FAIL indicate decisions for which the human majority label and the LLM label were identical. Percentages are calculated over non-null human–LLM decision pairs within each criterion.

Figure 7: Answer change by confidence percentile for each model on the test split. Confidence is measured by mean token log-probability of the original answer, with percentiles computed within each model. We include only originally correct cases and average negation forms within each question. Error bars show 95% question-bootstrap intervals.

Figure 8: Answer change by model and benchmark on the test split. The most frequent negated answer is identified within each model’s relation/type group using its test outputs. Rates are computed over originally correct pairs with a judged repetition outcome. Not evaluated indicates unavailable model–benchmark results.

Figure 9: Information flow in Gemma 3-12B-IT. Left: from negation tokens to other token groups and Right: from each group to the final prompt token.

Figure 10: Information flow in Gemma 3-4B-IT (top) and Llama 3.1-8B-Instruct (bottom). Left: paths from negation tokens. Right: paths to the final prompt token. Curves show normalized log-probability gap shift; shading shows 95% question-bootstrap intervals.

Figure 11: Information flow in Qwen3.5-9B, including softmax and linear attention. Final-position interventions continue during generation. Effects equally weight six benchmarks; shading shows 95% question-bootstrap intervals.

Model	Pairs	Layer	Match $\beta=0$	Match $\beta=1$	Gap shift $\beta=1$
Gemma 3-4B-IT	925	L18	13.8	40.1 [34.5, 46.4]	22.1 [18.3, 26.0]
Gemma 3-12B-IT	1540	L24	4.6	41.8 [37.2, 46.9]	24.6 [21.5, 28.0]
Llama 3.1-8B-Instruct	423	L24	19.6	19.7 [12.3, 27.8]	-1.2 [-4.9, 2.5]
Qwen3.5-9B	2304	L24	1.1	11.6 [8.2, 15.4]	0.5 [-0.7, 1.6]

Appendix

Table 10: Prompt-only negation-direction removal. Match denotes original-answer match rate; gap shift denotes normalized log-probability gap shift, both in percent. Brackets are 95% question-bootstrap intervals. Results equally weight six benchmarks for Gemma and Qwen, and four text benchmarks for Llama. The fixed dose layers are not uniformly the layerwise maxima; see the full sweeps.

Figure 12: Negation-direction removal in Gemma 3-4B-IT (top) and Gemma 3-12B-IT (bottom). Dose layers are L18 and L24; downstream alignment uses

\beta=3

and

\beta=2

, respectively. Effects equally weight six benchmarks. Shading shows available 95% question-bootstrap intervals; Gemma 12B downstream cosine is shown without a pooled interval.

Figure 13: Negation-direction removal in Llama 3.1-8B-Instruct (top; four text benchmarks) and Qwen3.5-9B (bottom; six benchmarks). Both displayed dose experiments use L24. Downstream alignment uses

\beta=1

and

\beta=2

, respectively.

Figure 14: Prompt-only negation-direction removal at L15 in Llama 3.1-8B-Instruct.

Intervention	$\Delta s(a)$	$\Delta s(b)$	Normalized gap shift (%)
Restore L31H13 answer-token contribution	$+0.129$	$-0.028$	$0.8$
Restore five head outputs	$+3.438$	$-2.336$	$21.4$
Restore 256 neuron activations	$+4.053$	$-2.467$	$24.7$
Restore both sets	$+4.937$	$-4.548$	$35.2$
Double 256 neuron differences	$-8.259$	$-1.057$	$-28.2$

Appendix

Table 11: Component interventions in Gemma 3-12B-IT, averaged across six benchmarks.

\Delta s(a)

and

\Delta s(b)

are changes in the original and alternative answers’ log-probabilities (nats); gap shift is the normalized log-probability gap shift toward the original prompt.

Model	Restored components	Match (%)	Gap shift (%)	Random gap shift (%)
Gemma 3-4B-IT	Five heads	52.4 [46.1, 58.7]	29.5 [26.2, 32.8]	12.0
Gemma 3-4B-IT	256 neurons	41.8 [36.6, 47.8]	22.0 [19.2, 24.9]	-0.3
Gemma 3-4B-IT	Both	59.6 [52.8, 66.3]	36.5 [33.3, 39.8]	12.0
Gemma 3-12B-IT	Five heads	37.4 [32.8, 43.0]	21.4 [18.5, 24.4]	2.1
Gemma 3-12B-IT	256 neurons	43.6 [39.0, 48.5]	24.7 [22.4, 26.8]	0.1
Gemma 3-12B-IT	Both	56.3 [50.7, 62.0]	35.2 [32.5, 38.0]	2.2

Appendix

Table 12: Prompt-only restoration of non-negated component values in negated prompts. Metrics and intervals follow Table 10 .

Model	Layer	Pairs	Match (%) Removal $\to$ restore	Gap shift (%) Removal $\to$ restore	Match difference (pp) Selected $-$ random
Gemma 3-4B-IT	L18	290	50.4 $\to$ 34.3	29.4 $\to$ 11.6	-12.3 [-19.3, -6.8]
Gemma 3-12B-IT	L24	612	56.6 $\to$ 17.4	32.3 $\to$ 9.2	-39.3 [-44.5, -34.1]
Llama 3.1-8B-Instruct	L14	368	21.3 $\to$ 13.6	21.0 $\to$ 9.3	-7.0 [-11.3, -3.4]
Qwen3.5-9B	L16	642	11.1 $\to$ 2.6	5.0 $\to$ 1.0	-7.7 [-10.0, -5.4]

Appendix

Table 13: Signal removal followed by joint restoration of selected heads and neurons at their natural negated values (

\beta=1

Figure 15: Signal removal followed by restoration of natural negated component values (

\beta=1

). Rows show (a) Gemma 3-4B-IT, (b) Gemma 3-12B-IT, (c) Llama 3.1-8B-Instruct, and (d) Qwen3.5-9B.

Model	Category	Layer	Pairs	Learned	Random	Full
Gemma 3-4B-IT	City	L23	64	29.9	0.1	35.0
Gemma 3-4B-IT	Person Name	L27	583	30.1	0.2	91.9
Gemma 3-4B-IT	Religion	L26	33	36.9	0.1	87.9
Gemma 3-4B-IT	Sport	L31	40	38.7	0.2	91.1
Gemma 3-12B-IT	City	L38	64	32.2	0.1	69.8
Gemma 3-12B-IT	Person Name	L42	583	32.4	0.2	74.2

Appendix

Table 14: Rank-4 candidate-space interventions between non-negated PopQA prompts with different answers in the same category.

Model	Layer	Pairs	Learned	Random	Full	Within-category answer gap
Gemma 3-4B-IT	L19	720	80.1 [69.9, 89.1]	0.2	70.3	4.2
Gemma 3-12B-IT	L27	720	74.3 [32.5, 104.2]	-1.7	108.8	4.6
Llama 3.1-8B-Instruct	L15	720	141.6 [58.0, 280.0]	0.4	62.2	3.8
Qwen3.5-9B	L19	720	103.5 [96.7, 111.6]	0.0	67.9	1.0

Appendix

Table 15: Rank-4 answer-category-space interventions between non-negated PopQA prompts.

Model	Pairs/ questions	Heads	Neurons	Both	Both $-$ random (pp)
Gemma 3-4B-IT	604/216	84.2	75.8	66.7	-30.2 [-34.9, -25.5]
Gemma 3-12B-IT	606/268	94.9	58.6	57.6	-40.9 [-45.7, -36.5]
Llama 3.1-8B-Instruct	473/202	97.2	63.7	64.0	-33.1 [-38.8, -27.7]
Qwen3.5-9B	527/206	91.7	60.0	54.3	-43.7 [-49.4, -38.4]

Appendix

Table 16: Original-answer match rate (%) on current-baseline repetition failures.

Figure 16: Interventions on repeated-answer failures in (a) Gemma 3-4B-IT, (b) Gemma 3-12B-IT, (c) Llama 3.1-8B-Instruct, and (d) Qwen3.5-9B. Left: original-answer match rate. Right: change in the original answer’s full-sequence log-probability relative to its unmodified negated baseline. Interventions continue during generation; error bars show 95% question-bootstrap intervals.

Model	Pairs	Success	Failure	Failure $-$ success
Gemma 3-4B-IT	966	1.187	0.276	-0.910 [-1.675, -0.241]
Gemma 3-12B-IT	1312	0.084	0.047	-0.038 [-0.124, 0.053]
Llama 3.1-8B-Instruct	1381	0.079	0.028	-0.051 [-0.120, 0.015]
Qwen3.5-9B	1206	0.148	0.085	-0.064 [-0.189, 0.031]

Appendix

Table 17: Support for the original answer supplied by the selected answer-token paths in prompts without negation.

Method	MMLU-Pro	HellaSwag	GSM8K	IFEval	General Avg.
Base	58.25	83.78	89.92	80.22	78.04
ALiT (ours)	57.65	83.44	89.23	80.41	77.68
Unlikelihood	57.46	83.23	89.61	81.52	77.95
SFT	56.06	82.95	88.86	80.04	76.98
DPO	56.53	83.42	89.08	80.41	77.36

Appendix

Table 18: general-capability results for Gemma-3-12B-IT checkpoints (%).

Figure 17: Answer change for Base, ALiT, and SFT, grouped by whether the original answer matches the most frequent negated answer. Arrows show percentage-point changes from Base within each group.

Explore similar work

How Language Models Process Negation
May 4, 2026Zhejian Zhou, Tianyi Zhou, Robin Jia +1Negation Large Language Models Fail
Information Sciences Institute, University of Southern California · Thomas Lord Department of Computer Science, University of Southern California
Negation Neglect: When models fail to learn negations in training
May 13, 2026Harry Mayne, Lev McKinney, Jan Dubiński +3Negation Artificial Intelligence Safety
University of Oxford · University of Toronto · 3Warsaw University of Technology +6
Revisiting the Systematicity in Negation in the Era of In-Context Learning
Jun 15, 2026Hitomi Yanaka, Taisei YamamotoNegation Large Language Models Fail
The University of Tokyo · Riken · Tohoku University

May 4, 2026, cs.CLJ/K move · Enter open · S save

How Language Models Process Negation

Zhejian Zhou, Tianyi Zhou, Robin Jia, Jonathan May

Information Sciences Institute, University of Southern California · Thomas Lord Department of Computer Science, University of Southern California

Negation Large Language Models Fail Causal Inferences

Open paper AskPDF arXiv

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that process negation correctly. Their poor accuracy is due to late-layer attention behavior that promotes simple shortcuts; ablating those attention modules greatly improves accuracy on negation-related questions. Second, we uncover how models process negation. We consider two hypotheses: models could use attention heads that attend to the phrase being negated and suppress related concepts, or they could directly construct a representation of the entire negative phrase (e.g., representing "not gas" as a vector that promotes liquids and solids). We apply a range of observational and causal interpretability techniques on Mistral-7B and Llama-3.1-8B to show that models implement both mechanisms, with the "constructive" mechanism being more prominent. Combined, our work deepens the understanding of LLMs' internals, highlighting construction-dominant computations and the coexistence of competing mechanisms within LLMs.

Abstract

Explore similar work

How Language Models Process Negation

Negation Neglect: When models fail to learn negations in training

Revisiting the Systematicity in Negation in the Era of In-Context Learning